Add SkateFormer (ECCV 2024) checkpoints with PyTorchModelHubMixin support

README.md

@@ -0,0 +1,153 @@
+---
+library_name: skateformer
+license: mit
+pipeline_tag: video-classification
+tags:
+- skeleton-action-recognition
+- action-recognition
+- transformer
+- eccv2024
+- pytorch
+---
+
+# SkateFormer
+
+Official checkpoints for [SkateFormer: Skeletal-Temporal Transformer for Human Action
+Recognition](https://huggingface.co/papers/2403.09508) (ECCV 2024).
+
+SkateFormer partitions joints and frames into four *Skate-Types* (neighbouring/distant
+joints × local/global frames) and applies **Skate-MSA** within each partition, so attention
+is spent on the skeletal-temporal relations that actually matter for an action instead of
+on all joint-frame pairs. At 2.0-3.6M parameters it reaches state-of-the-art accuracy on
+NTU RGB+D, NTU RGB+D 120, NTU-Inter and NW-UCLA.
+
+- 📄 Paper: https://huggingface.co/papers/2403.09508
+- 🏠 Project page: https://kaist-viclab.github.io/SkateFormer_site/
+- 💻 Code: https://github.com/KAIST-VICLab/SkateFormer
+
+## Checkpoints
+
+All 14 released checkpoints live in this one repository, one directory each. Select one
+with the `subfolder` argument.
+
+| `subfolder` | Dataset | Protocol | Modality | Classes | Params | Top-1 |
+|---|---|---|---|---|---|---|
+| `ntu60-xsub-joint` | NTU RGB+D 60 | X-Sub | joint | 60 | 3.62M | **92.6%** <br><sub>J+B: 93.0%</sub> |
+| `ntu60-xsub-bone` | NTU RGB+D 60 | X-Sub | bone | 60 | 3.62M | **92.1%** <br><sub>J+B: 93.0%</sub> |
+| `ntu60-xview-joint` | NTU RGB+D 60 | X-View | joint | 60 | 3.62M | **97.0%** <br><sub>J+B: 97.4%</sub> |
+| `ntu60-xview-bone` | NTU RGB+D 60 | X-View | bone | 60 | 3.62M | **96.5%** <br><sub>J+B: 97.4%</sub> |
+| `ntu120-xsub-joint` | NTU RGB+D 120 | X-Sub | joint | 120 | 3.63M | **87.7%** <br><sub>J+B: 89.4%</sub> |
+| `ntu120-xsub-bone` | NTU RGB+D 120 | X-Sub | bone | 120 | 3.63M | **88.2%** <br><sub>J+B: 89.4%</sub> |
+| `ntu120-xset-joint` | NTU RGB+D 120 | X-Set | joint | 120 | 3.63M | **89.3%** <br><sub>J+B: 91.0%</sub> |
+| `ntu120-xset-bone` | NTU RGB+D 120 | X-Set | bone | 120 | 3.63M | **89.8%** <br><sub>J+B: 91.0%</sub> |
+| `ntu60-inter-xsub-joint` | NTU-Inter | X-Sub | joint | 11 | 3.61M | **97.1%** |
+| `ntu60-inter-xview-joint` | NTU-Inter | X-View | joint | 11 | 3.61M | **99.3%** |
+| `ntu120-inter-xsub-joint` | NTU-Inter 120 | X-Sub | joint | 26 | 3.61M | **92.3%** |
+| `ntu120-inter-xset-joint` | NTU-Inter 120 | X-Set | joint | 26 | 3.61M | **93.2%** |
+| `nwucla-joint` | NW-UCLA | official split | joint | 10 | 1.93M | 98.3% |
+| `nwucla-bone` | NW-UCLA | official split | bone | 10 | 1.93M | 98.3% |
+
+Accuracy is the top-1 figure reported in the paper. `J+B` is the E2 ensemble — average the
+softmax outputs of the joint and bone checkpoints of the same row pair. The paper reports a
+single NW-UCLA figure with no per-modality or per-ensemble breakdown, so it is listed once
+rather than attributed to either stream.
+
+## Usage
+
+```bash
+pip install torch timm huggingface_hub safetensors
+pip install git+https://github.com/KAIST-VICLab/SkateFormer.git
+```
+
+```python
+import torch
+from skateformer import SkateFormer
+
+model = SkateFormer.from_pretrained(
+    "JeonghyeokDo/SkateFormer", subfolder="ntu60-xsub-joint"
+).eval()
+
+# [B, C, T, V, M] — already joint-partitioned, see below
+x = torch.randn(1, 3, 64, 24, 2)
+with torch.no_grad():
+    logits = model(x)                      # -> [1, 60]
+
+print(model.id2label[logits.argmax(-1).item()])
+```
+
+### Preprocessing
+
+SkateFormer does not take raw skeletons directly. A sequence must be (1) converted to the
+requested modality, (2) resampled to a 64-frame clip, and (3) reordered into skeletal
+partitions. `skateformer.preprocessing` reproduces the evaluation-time path of the original
+feeders:
+
+```python
+import numpy as np
+from skateformer.preprocessing import prepare_input
+
+raw = np.random.randn(3, 300, 25, 2)   # [C, T, V, M] raw NTU skeleton (25 joints, 2 people)
+x, index_t = prepare_input(raw, valid_frame_num=120, layout="ntu", modality="j")
+
+with torch.no_grad():
+    logits = model(x, index_t)
+```
+
+Use `layout="nw_ucla"` (20 joints, 1 person) for the NW-UCLA checkpoints, and
+`modality="b"` for the bone ones — the modality must match the checkpoint you loaded.
+
+`index_t` carries the normalised timestamps of the sampled frames (in `[-1, 1]`) and drives
+the model's temporal index embedding. If omitted, the model assumes a clip that uniformly
+spans the whole sequence.
+
+### Two-stream ensemble
+
+```python
+joint = SkateFormer.from_pretrained("JeonghyeokDo/SkateFormer", subfolder="ntu60-xsub-joint").eval()
+bone = SkateFormer.from_pretrained("JeonghyeokDo/SkateFormer", subfolder="ntu60-xsub-bone").eval()
+
+xj, t = prepare_input(raw, valid_frame_num=120, layout="ntu", modality="j")
+xb, _ = prepare_input(raw, valid_frame_num=120, layout="ntu", modality="b")
+with torch.no_grad():
+    probs = (joint(xj, t).softmax(-1) + bone(xb, t).softmax(-1)) / 2
+```
+
+## Classes
+
+`model.id2label` maps class ids to names for the loaded checkpoint. The label sets are
+NTU RGB+D 60 (60), NTU RGB+D 120 (120), NTU-Inter (11: A50-A60), NTU-Inter 120
+(26: A50-A60 + A106-A120) and NW-UCLA (10):
+
+0. pick up with one hand
+1. pick up with two hands
+2. drop trash
+3. walk around
+4. sit down
+5. stand up
+6. donning
+7. doffing
+8. throw
+9. carry
+
+## Limitations
+
+- Each checkpoint is trained on one dataset; accuracy drops on skeletons from a different
+  pose estimator or joint layout without fine-tuning.
+- The joint partition order is part of the model: feeding un-partitioned joints silently
+  produces wrong predictions.
+
+## License
+
+MIT, as in the [original repository](https://github.com/KAIST-VICLab/SkateFormer/blob/main/LICENSE).
+The underlying datasets (NTU RGB+D, NTU RGB+D 120, NW-UCLA) carry their own terms.
+
+## Citation
+
+```bibtex
+@inproceedings{do2024skateformer,
+  title     = {SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition},
+  author    = {Do, Jeonghyeok and Kim, Munchurl},
+  booktitle = {European Conference on Computer Vision (ECCV)},
+  year      = {2024}
+}
+```

ntu120-inter-xset-joint/README.md

@@ -0,0 +1,18 @@
+---
+library_name: skateformer
+license: mit
+pipeline_tag: video-classification
+tags:
+- action-recognition
+- eccv2024
+- model_hub_mixin
+- pytorch
+- pytorch_model_hub_mixin
+- skeleton-action-recognition
+- transformer
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Code: https://github.com/KAIST-VICLab/SkateFormer
+- Paper: https://huggingface.co/papers/2403.09508
+- Docs: https://kaist-viclab.github.io/SkateFormer_site/

ntu120-inter-xset-joint/config.json

@@ -0,0 +1,74 @@
+{
+  "attn_drop": 0.5,
+  "channels": [
+    96,
+    192,
+    192,
+    192
+  ],
+  "depths": [
+    2,
+    2,
+    2,
+    2
+  ],
+  "drop": 0.0,
+  "drop_path": 0.2,
+  "embed_dim": 96,
+  "global_pool": "avg",
+  "head_drop": 0.0,
+  "id2label": {
+    "0": "punching/slapping other person",
+    "1": "kicking other person",
+    "2": "pushing other person",
+    "3": "pat on back of other person",
+    "4": "point finger at the other person",
+    "5": "hugging other person",
+    "6": "giving something to other person",
+    "7": "touch other person's pocket",
+    "8": "handshaking",
+    "9": "walking towards each other",
+    "10": "walking apart from each other",
+    "11": "hit other person with something",
+    "12": "wield knife towards other person",
+    "13": "knock over other person (hit with body)",
+    "14": "grab other person's stuff",
+    "15": "shoot at other person with a gun",
+    "16": "step on foot",
+    "17": "high-five",
+    "18": "cheers and drink",
+    "19": "carry something with other person",
+    "20": "take a photo of other person",
+    "21": "follow other person",
+    "22": "whisper in other person's ear",
+    "23": "exchange things with other person",
+    "24": "support somebody with hand",
+    "25": "finger-guessing game (playing rock-paper-scissors)"
+  },
+  "in_channels": 3,
+  "index_t": true,
+  "kernel_size": 7,
+  "mlp_ratio": 4.0,
+  "num_classes": 26,
+  "num_frames": 64,
+  "num_heads": 32,
+  "num_people": 2,
+  "num_points": 24,
+  "rel": true,
+  "type_1_size": [
+    8,
+    8
+  ],
+  "type_2_size": [
+    8,
+    12
+  ],
+  "type_3_size": [
+    8,
+    8
+  ],
+  "type_4_size": [
+    8,
+    12
+  ]
+}

ntu120-inter-xset-joint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4af9a5adab802dcae225ad7fb3f7e84cd4e7026d2291c2300910c5c68cfd5b3e
+size 14483700

ntu120-inter-xsub-joint/README.md

@@ -0,0 +1,18 @@
+---
+library_name: skateformer
+license: mit
+pipeline_tag: video-classification
+tags:
+- action-recognition
+- eccv2024
+- model_hub_mixin
+- pytorch
+- pytorch_model_hub_mixin
+- skeleton-action-recognition
+- transformer
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Code: https://github.com/KAIST-VICLab/SkateFormer
+- Paper: https://huggingface.co/papers/2403.09508
+- Docs: https://kaist-viclab.github.io/SkateFormer_site/

ntu120-inter-xsub-joint/config.json

@@ -0,0 +1,74 @@
+{
+  "attn_drop": 0.5,
+  "channels": [
+    96,
+    192,
+    192,
+    192
+  ],
+  "depths": [
+    2,
+    2,
+    2,
+    2
+  ],
+  "drop": 0.0,
+  "drop_path": 0.2,
+  "embed_dim": 96,
+  "global_pool": "avg",
+  "head_drop": 0.0,
+  "id2label": {
+    "0": "punching/slapping other person",
+    "1": "kicking other person",
+    "2": "pushing other person",
+    "3": "pat on back of other person",
+    "4": "point finger at the other person",
+    "5": "hugging other person",
+    "6": "giving something to other person",
+    "7": "touch other person's pocket",
+    "8": "handshaking",
+    "9": "walking towards each other",
+    "10": "walking apart from each other",
+    "11": "hit other person with something",
+    "12": "wield knife towards other person",
+    "13": "knock over other person (hit with body)",
+    "14": "grab other person's stuff",
+    "15": "shoot at other person with a gun",
+    "16": "step on foot",
+    "17": "high-five",
+    "18": "cheers and drink",
+    "19": "carry something with other person",
+    "20": "take a photo of other person",
+    "21": "follow other person",
+    "22": "whisper in other person's ear",
+    "23": "exchange things with other person",
+    "24": "support somebody with hand",
+    "25": "finger-guessing game (playing rock-paper-scissors)"
+  },
+  "in_channels": 3,
+  "index_t": true,
+  "kernel_size": 7,
+  "mlp_ratio": 4.0,
+  "num_classes": 26,
+  "num_frames": 64,
+  "num_heads": 32,
+  "num_people": 2,
+  "num_points": 24,
+  "rel": true,
+  "type_1_size": [
+    8,
+    8
+  ],
+  "type_2_size": [
+    8,
+    12
+  ],
+  "type_3_size": [
+    8,
+    8
+  ],
+  "type_4_size": [
+    8,
+    12
+  ]
+}

ntu120-inter-xsub-joint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8968d134c20a276a293cbf51bebdbb9a385fb4b6eb1e1e497e21025fce990020
+size 14483700

ntu120-xset-bone/README.md

@@ -0,0 +1,18 @@
+---
+library_name: skateformer
+license: mit
+pipeline_tag: video-classification
+tags:
+- action-recognition
+- eccv2024
+- model_hub_mixin
+- pytorch
+- pytorch_model_hub_mixin
+- skeleton-action-recognition
+- transformer
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Code: https://github.com/KAIST-VICLab/SkateFormer
+- Paper: https://huggingface.co/papers/2403.09508
+- Docs: https://kaist-viclab.github.io/SkateFormer_site/

ntu120-xset-bone/config.json

@@ -0,0 +1,168 @@
+{
+  "attn_drop": 0.5,
+  "channels": [
+    96,
+    192,
+    192,
+    192
+  ],
+  "depths": [
+    2,
+    2,
+    2,
+    2
+  ],
+  "drop": 0.0,
+  "drop_path": 0.2,
+  "embed_dim": 96,
+  "global_pool": "avg",
+  "head_drop": 0.0,
+  "id2label": {
+    "0": "drink water",
+    "1": "eat meal/snack",
+    "2": "brushing teeth",
+    "3": "brushing hair",
+    "4": "drop",
+    "5": "pickup",
+    "6": "throw",
+    "7": "sitting down",
+    "8": "standing up (from sitting position)",
+    "9": "clapping",
+    "10": "reading",
+    "11": "writing",
+    "12": "tear up paper",
+    "13": "wear jacket",
+    "14": "take off jacket",
+    "15": "wear a shoe",
+    "16": "take off a shoe",
+    "17": "wear on glasses",
+    "18": "take off glasses",
+    "19": "put on a hat/cap",
+    "20": "take off a hat/cap",
+    "21": "cheer up",
+    "22": "hand waving",
+    "23": "kicking something",
+    "24": "reach into pocket",
+    "25": "hopping (one foot jumping)",
+    "26": "jump up",
+    "27": "make a phone call/answer phone",
+    "28": "playing with phone/tablet",
+    "29": "typing on a keyboard",
+    "30": "pointing to something with finger",
+    "31": "taking a selfie",
+    "32": "check time (from watch)",
+    "33": "rub two hands together",
+    "34": "nod head/bow",
+    "35": "shake head",
+    "36": "wipe face",
+    "37": "salute",
+    "38": "put the palms together",
+    "39": "cross hands in front (say stop)",
+    "40": "sneeze/cough",
+    "41": "staggering",
+    "42": "falling",
+    "43": "touch head (headache)",
+    "44": "touch chest (stomachache/heart pain)",
+    "45": "touch back (backache)",
+    "46": "touch neck (neckache)",
+    "47": "nausea or vomiting condition",
+    "48": "use a fan (with hand or paper)/feeling warm",
+    "49": "punching/slapping other person",
+    "50": "kicking other person",
+    "51": "pushing other person",
+    "52": "pat on back of other person",
+    "53": "point finger at the other person",
+    "54": "hugging other person",
+    "55": "giving something to other person",
+    "56": "touch other person's pocket",
+    "57": "handshaking",
+    "58": "walking towards each other",
+    "59": "walking apart from each other",
+    "60": "put on headphone",
+    "61": "take off headphone",
+    "62": "shoot at the basket",
+    "63": "bounce ball",
+    "64": "tennis bat swing",
+    "65": "juggling table tennis balls",
+    "66": "hush (quiet)",
+    "67": "flick hair",
+    "68": "thumb up",
+    "69": "thumb down",
+    "70": "make ok sign",
+    "71": "make victory sign",
+    "72": "staple book",
+    "73": "counting money",
+    "74": "cutting nails",
+    "75": "cutting paper (using scissors)",
+    "76": "snapping fingers",
+    "77": "open bottle",
+    "78": "sniff (smell)",
+    "79": "squat down",
+    "80": "toss a coin",
+    "81": "fold paper",
+    "82": "ball up paper",
+    "83": "play magic cube",
+    "84": "apply cream on face",
+    "85": "apply cream on hand back",
+    "86": "put on bag",
+    "87": "take off bag",
+    "88": "put something into a bag",
+    "89": "take something out of a bag",
+    "90": "open a box",
+    "91": "move heavy objects",
+    "92": "shake fist",
+    "93": "throw up cap/hat",
+    "94": "hands up (both hands)",
+    "95": "cross arms",
+    "96": "arm circles",
+    "97": "arm swings",
+    "98": "running on the spot",
+    "99": "butt kicks (kick backward)",
+    "100": "cross toe touch",
+    "101": "side kick",
+    "102": "yawn",
+    "103": "stretch oneself",
+    "104": "blow nose",
+    "105": "hit other person with something",
+    "106": "wield knife towards other person",
+    "107": "knock over other person (hit with body)",
+    "108": "grab other person's stuff",
+    "109": "shoot at other person with a gun",
+    "110": "step on foot",
+    "111": "high-five",
+    "112": "cheers and drink",
+    "113": "carry something with other person",
+    "114": "take a photo of other person",
+    "115": "follow other person",
+    "116": "whisper in other person's ear",
+    "117": "exchange things with other person",
+    "118": "support somebody with hand",
+    "119": "finger-guessing game (playing rock-paper-scissors)"
+  },
+  "in_channels": 3,
+  "index_t": true,
+  "kernel_size": 7,
+  "mlp_ratio": 4.0,
+  "num_classes": 120,
+  "num_frames": 64,
+  "num_heads": 32,
+  "num_people": 2,
+  "num_points": 24,
+  "rel": true,
+  "type_1_size": [
+    8,
+    8
+  ],
+  "type_2_size": [
+    8,
+    12
+  ],
+  "type_3_size": [
+    8,
+    8
+  ],
+  "type_4_size": [
+    8,
+    12
+  ]
+}

ntu120-xset-bone/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a07971aa64c9028d09708161276bbe266cdf7cd9b8701d4d634899e1403e35c4
+size 14556284

ntu120-xset-joint/README.md

@@ -0,0 +1,18 @@
+---
+library_name: skateformer
+license: mit
+pipeline_tag: video-classification
+tags:
+- action-recognition
+- eccv2024
+- model_hub_mixin
+- pytorch
+- pytorch_model_hub_mixin
+- skeleton-action-recognition
+- transformer
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Code: https://github.com/KAIST-VICLab/SkateFormer
+- Paper: https://huggingface.co/papers/2403.09508
+- Docs: https://kaist-viclab.github.io/SkateFormer_site/

ntu120-xset-joint/config.json

@@ -0,0 +1,168 @@
+{
+  "attn_drop": 0.5,
+  "channels": [
+    96,
+    192,
+    192,
+    192
+  ],
+  "depths": [
+    2,
+    2,
+    2,
+    2
+  ],
+  "drop": 0.0,
+  "drop_path": 0.2,
+  "embed_dim": 96,
+  "global_pool": "avg",
+  "head_drop": 0.0,
+  "id2label": {
+    "0": "drink water",
+    "1": "eat meal/snack",
+    "2": "brushing teeth",
+    "3": "brushing hair",
+    "4": "drop",
+    "5": "pickup",
+    "6": "throw",
+    "7": "sitting down",
+    "8": "standing up (from sitting position)",
+    "9": "clapping",
+    "10": "reading",
+    "11": "writing",
+    "12": "tear up paper",
+    "13": "wear jacket",
+    "14": "take off jacket",
+    "15": "wear a shoe",
+    "16": "take off a shoe",
+    "17": "wear on glasses",
+    "18": "take off glasses",
+    "19": "put on a hat/cap",
+    "20": "take off a hat/cap",
+    "21": "cheer up",
+    "22": "hand waving",
+    "23": "kicking something",
+    "24": "reach into pocket",
+    "25": "hopping (one foot jumping)",
+    "26": "jump up",
+    "27": "make a phone call/answer phone",
+    "28": "playing with phone/tablet",
+    "29": "typing on a keyboard",
+    "30": "pointing to something with finger",
+    "31": "taking a selfie",
+    "32": "check time (from watch)",
+    "33": "rub two hands together",
+    "34": "nod head/bow",
+    "35": "shake head",
+    "36": "wipe face",
+    "37": "salute",
+    "38": "put the palms together",
+    "39": "cross hands in front (say stop)",
+    "40": "sneeze/cough",
+    "41": "staggering",
+    "42": "falling",
+    "43": "touch head (headache)",
+    "44": "touch chest (stomachache/heart pain)",
+    "45": "touch back (backache)",
+    "46": "touch neck (neckache)",
+    "47": "nausea or vomiting condition",
+    "48": "use a fan (with hand or paper)/feeling warm",
+    "49": "punching/slapping other person",
+    "50": "kicking other person",
+    "51": "pushing other person",
+    "52": "pat on back of other person",
+    "53": "point finger at the other person",
+    "54": "hugging other person",
+    "55": "giving something to other person",
+    "56": "touch other person's pocket",
+    "57": "handshaking",
+    "58": "walking towards each other",
+    "59": "walking apart from each other",
+    "60": "put on headphone",
+    "61": "take off headphone",
+    "62": "shoot at the basket",
+    "63": "bounce ball",
+    "64": "tennis bat swing",
+    "65": "juggling table tennis balls",
+    "66": "hush (quiet)",
+    "67": "flick hair",
+    "68": "thumb up",
+    "69": "thumb down",
+    "70": "make ok sign",
+    "71": "make victory sign",
+    "72": "staple book",
+    "73": "counting money",
+    "74": "cutting nails",
+    "75": "cutting paper (using scissors)",
+    "76": "snapping fingers",
+    "77": "open bottle",
+    "78": "sniff (smell)",
+    "79": "squat down",
+    "80": "toss a coin",
+    "81": "fold paper",
+    "82": "ball up paper",
+    "83": "play magic cube",
+    "84": "apply cream on face",
+    "85": "apply cream on hand back",
+    "86": "put on bag",
+    "87": "take off bag",
+    "88": "put something into a bag",
+    "89": "take something out of a bag",
+    "90": "open a box",
+    "91": "move heavy objects",
+    "92": "shake fist",
+    "93": "throw up cap/hat",
+    "94": "hands up (both hands)",
+    "95": "cross arms",
+    "96": "arm circles",
+    "97": "arm swings",
+    "98": "running on the spot",
+    "99": "butt kicks (kick backward)",
+    "100": "cross toe touch",
+    "101": "side kick",
+    "102": "yawn",
+    "103": "stretch oneself",
+    "104": "blow nose",
+    "105": "hit other person with something",
+    "106": "wield knife towards other person",
+    "107": "knock over other person (hit with body)",
+    "108": "grab other person's stuff",
+    "109": "shoot at other person with a gun",
+    "110": "step on foot",
+    "111": "high-five",
+    "112": "cheers and drink",
+    "113": "carry something with other person",
+    "114": "take a photo of other person",
+    "115": "follow other person",
+    "116": "whisper in other person's ear",
+    "117": "exchange things with other person",
+    "118": "support somebody with hand",
+    "119": "finger-guessing game (playing rock-paper-scissors)"
+  },
+  "in_channels": 3,
+  "index_t": true,
+  "kernel_size": 7,
+  "mlp_ratio": 4.0,
+  "num_classes": 120,
+  "num_frames": 64,
+  "num_heads": 32,
+  "num_people": 2,
+  "num_points": 24,
+  "rel": true,
+  "type_1_size": [
+    8,
+    8
+  ],
+  "type_2_size": [
+    8,
+    12
+  ],
+  "type_3_size": [
+    8,
+    8
+  ],
+  "type_4_size": [
+    8,
+    12
+  ]
+}

ntu120-xset-joint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd56ca02853f2744b5151050b87cf5e72c74bffa1135c5a5b3206f33d2c9bff2
+size 14556284

ntu120-xsub-bone/README.md

@@ -0,0 +1,18 @@
+---
+library_name: skateformer
+license: mit
+pipeline_tag: video-classification
+tags:
+- action-recognition
+- eccv2024
+- model_hub_mixin
+- pytorch
+- pytorch_model_hub_mixin
+- skeleton-action-recognition
+- transformer
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Code: https://github.com/KAIST-VICLab/SkateFormer
+- Paper: https://huggingface.co/papers/2403.09508
+- Docs: https://kaist-viclab.github.io/SkateFormer_site/

ntu120-xsub-bone/config.json

@@ -0,0 +1,168 @@
+{
+  "attn_drop": 0.5,
+  "channels": [
+    96,
+    192,
+    192,
+    192
+  ],
+  "depths": [
+    2,
+    2,
+    2,
+    2
+  ],
+  "drop": 0.0,
+  "drop_path": 0.2,
+  "embed_dim": 96,
+  "global_pool": "avg",
+  "head_drop": 0.0,
+  "id2label": {
+    "0": "drink water",
+    "1": "eat meal/snack",
+    "2": "brushing teeth",
+    "3": "brushing hair",
+    "4": "drop",
+    "5": "pickup",
+    "6": "throw",
+    "7": "sitting down",
+    "8": "standing up (from sitting position)",
+    "9": "clapping",
+    "10": "reading",
+    "11": "writing",
+    "12": "tear up paper",
+    "13": "wear jacket",
+    "14": "take off jacket",
+    "15": "wear a shoe",
+    "16": "take off a shoe",
+    "17": "wear on glasses",
+    "18": "take off glasses",
+    "19": "put on a hat/cap",
+    "20": "take off a hat/cap",
+    "21": "cheer up",
+    "22": "hand waving",
+    "23": "kicking something",
+    "24": "reach into pocket",
+    "25": "hopping (one foot jumping)",
+    "26": "jump up",
+    "27": "make a phone call/answer phone",
+    "28": "playing with phone/tablet",
+    "29": "typing on a keyboard",
+    "30": "pointing to something with finger",
+    "31": "taking a selfie",
+    "32": "check time (from watch)",
+    "33": "rub two hands together",
+    "34": "nod head/bow",
+    "35": "shake head",
+    "36": "wipe face",
+    "37": "salute",
+    "38": "put the palms together",
+    "39": "cross hands in front (say stop)",
+    "40": "sneeze/cough",
+    "41": "staggering",
+    "42": "falling",
+    "43": "touch head (headache)",
+    "44": "touch chest (stomachache/heart pain)",
+    "45": "touch back (backache)",
+    "46": "touch neck (neckache)",
+    "47": "nausea or vomiting condition",
+    "48": "use a fan (with hand or paper)/feeling warm",
+    "49": "punching/slapping other person",
+    "50": "kicking other person",
+    "51": "pushing other person",
+    "52": "pat on back of other person",
+    "53": "point finger at the other person",
+    "54": "hugging other person",
+    "55": "giving something to other person",
+    "56": "touch other person's pocket",
+    "57": "handshaking",
+    "58": "walking towards each other",
+    "59": "walking apart from each other",
+    "60": "put on headphone",
+    "61": "take off headphone",
+    "62": "shoot at the basket",
+    "63": "bounce ball",
+    "64": "tennis bat swing",
+    "65": "juggling table tennis balls",
+    "66": "hush (quiet)",
+    "67": "flick hair",
+    "68": "thumb up",
+    "69": "thumb down",
+    "70": "make ok sign",
+    "71": "make victory sign",
+    "72": "staple book",
+    "73": "counting money",
+    "74": "cutting nails",
+    "75": "cutting paper (using scissors)",
+    "76": "snapping fingers",
+    "77": "open bottle",
+    "78": "sniff (smell)",
+    "79": "squat down",
+    "80": "toss a coin",
+    "81": "fold paper",
+    "82": "ball up paper",
+    "83": "play magic cube",
+    "84": "apply cream on face",
+    "85": "apply cream on hand back",
+    "86": "put on bag",
+    "87": "take off bag",
+    "88": "put something into a bag",
+    "89": "take something out of a bag",
+    "90": "open a box",
+    "91": "move heavy objects",
+    "92": "shake fist",
+    "93": "throw up cap/hat",
+    "94": "hands up (both hands)",
+    "95": "cross arms",
+    "96": "arm circles",
+    "97": "arm swings",
+    "98": "running on the spot",
+    "99": "butt kicks (kick backward)",
+    "100": "cross toe touch",
+    "101": "side kick",
+    "102": "yawn",
+    "103": "stretch oneself",
+    "104": "blow nose",
+    "105": "hit other person with something",
+    "106": "wield knife towards other person",
+    "107": "knock over other person (hit with body)",
+    "108": "grab other person's stuff",
+    "109": "shoot at other person with a gun",
+    "110": "step on foot",
+    "111": "high-five",
+    "112": "cheers and drink",
+    "113": "carry something with other person",
+    "114": "take a photo of other person",
+    "115": "follow other person",
+    "116": "whisper in other person's ear",
+    "117": "exchange things with other person",
+    "118": "support somebody with hand",
+    "119": "finger-guessing game (playing rock-paper-scissors)"
+  },
+  "in_channels": 3,
+  "index_t": true,
+  "kernel_size": 7,
+  "mlp_ratio": 4.0,
+  "num_classes": 120,
+  "num_frames": 64,
+  "num_heads": 32,
+  "num_people": 2,
+  "num_points": 24,
+  "rel": true,
+  "type_1_size": [
+    8,
+    8
+  ],
+  "type_2_size": [
+    8,
+    12
+  ],
+  "type_3_size": [
+    8,
+    8
+  ],
+  "type_4_size": [
+    8,
+    12
+  ]
+}

ntu120-xsub-bone/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deb19c175afd9e0cdbb14bf47ff8b998073b775f603d3533babc5bcb0a0b966a
+size 14556284

ntu120-xsub-joint/README.md

@@ -0,0 +1,18 @@
+---
+library_name: skateformer
+license: mit
+pipeline_tag: video-classification
+tags:
+- action-recognition
+- eccv2024
+- model_hub_mixin
+- pytorch
+- pytorch_model_hub_mixin
+- skeleton-action-recognition
+- transformer
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Code: https://github.com/KAIST-VICLab/SkateFormer
+- Paper: https://huggingface.co/papers/2403.09508
+- Docs: https://kaist-viclab.github.io/SkateFormer_site/

ntu120-xsub-joint/config.json

@@ -0,0 +1,168 @@
+{
+  "attn_drop": 0.5,
+  "channels": [
+    96,
+    192,
+    192,
+    192
+  ],
+  "depths": [
+    2,
+    2,
+    2,
+    2
+  ],
+  "drop": 0.0,
+  "drop_path": 0.2,
+  "embed_dim": 96,
+  "global_pool": "avg",
+  "head_drop": 0.0,
+  "id2label": {
+    "0": "drink water",
+    "1": "eat meal/snack",
+    "2": "brushing teeth",
+    "3": "brushing hair",
+    "4": "drop",
+    "5": "pickup",
+    "6": "throw",
+    "7": "sitting down",
+    "8": "standing up (from sitting position)",
+    "9": "clapping",
+    "10": "reading",
+    "11": "writing",
+    "12": "tear up paper",
+    "13": "wear jacket",
+    "14": "take off jacket",
+    "15": "wear a shoe",
+    "16": "take off a shoe",
+    "17": "wear on glasses",
+    "18": "take off glasses",
+    "19": "put on a hat/cap",
+    "20": "take off a hat/cap",
+    "21": "cheer up",
+    "22": "hand waving",
+    "23": "kicking something",
+    "24": "reach into pocket",
+    "25": "hopping (one foot jumping)",
+    "26": "jump up",
+    "27": "make a phone call/answer phone",
+    "28": "playing with phone/tablet",
+    "29": "typing on a keyboard",
+    "30": "pointing to something with finger",
+    "31": "taking a selfie",
+    "32": "check time (from watch)",
+    "33": "rub two hands together",
+    "34": "nod head/bow",
+    "35": "shake head",
+    "36": "wipe face",
+    "37": "salute",
+    "38": "put the palms together",
+    "39": "cross hands in front (say stop)",
+    "40": "sneeze/cough",
+    "41": "staggering",
+    "42": "falling",
+    "43": "touch head (headache)",
+    "44": "touch chest (stomachache/heart pain)",
+    "45": "touch back (backache)",
+    "46": "touch neck (neckache)",
+    "47": "nausea or vomiting condition",
+    "48": "use a fan (with hand or paper)/feeling warm",
+    "49": "punching/slapping other person",
+    "50": "kicking other person",
+    "51": "pushing other person",
+    "52": "pat on back of other person",
+    "53": "point finger at the other person",
+    "54": "hugging other person",
+    "55": "giving something to other person",
+    "56": "touch other person's pocket",
+    "57": "handshaking",
+    "58": "walking towards each other",
+    "59": "walking apart from each other",
+    "60": "put on headphone",
+    "61": "take off headphone",
+    "62": "shoot at the basket",
+    "63": "bounce ball",
+    "64": "tennis bat swing",
+    "65": "juggling table tennis balls",
+    "66": "hush (quiet)",
+    "67": "flick hair",
+    "68": "thumb up",
+    "69": "thumb down",
+    "70": "make ok sign",
+    "71": "make victory sign",
+    "72": "staple book",
+    "73": "counting money",
+    "74": "cutting nails",
+    "75": "cutting paper (using scissors)",
+    "76": "snapping fingers",
+    "77": "open bottle",
+    "78": "sniff (smell)",
+    "79": "squat down",
+    "80": "toss a coin",
+    "81": "fold paper",
+    "82": "ball up paper",
+    "83": "play magic cube",
+    "84": "apply cream on face",
+    "85": "apply cream on hand back",
+    "86": "put on bag",
+    "87": "take off bag",
+    "88": "put something into a bag",
+    "89": "take something out of a bag",
+    "90": "open a box",
+    "91": "move heavy objects",
+    "92": "shake fist",
+    "93": "throw up cap/hat",
+    "94": "hands up (both hands)",
+    "95": "cross arms",
+    "96": "arm circles",
+    "97": "arm swings",
+    "98": "running on the spot",
+    "99": "butt kicks (kick backward)",
+    "100": "cross toe touch",
+    "101": "side kick",
+    "102": "yawn",
+    "103": "stretch oneself",
+    "104": "blow nose",
+    "105": "hit other person with something",
+    "106": "wield knife towards other person",
+    "107": "knock over other person (hit with body)",
+    "108": "grab other person's stuff",
+    "109": "shoot at other person with a gun",
+    "110": "step on foot",
+    "111": "high-five",
+    "112": "cheers and drink",
+    "113": "carry something with other person",
+    "114": "take a photo of other person",
+    "115": "follow other person",
+    "116": "whisper in other person's ear",
+    "117": "exchange things with other person",
+    "118": "support somebody with hand",
+    "119": "finger-guessing game (playing rock-paper-scissors)"
+  },
+  "in_channels": 3,
+  "index_t": true,
+  "kernel_size": 7,
+  "mlp_ratio": 4.0,
+  "num_classes": 120,
+  "num_frames": 64,
+  "num_heads": 32,
+  "num_people": 2,
+  "num_points": 24,
+  "rel": true,
+  "type_1_size": [
+    8,
+    8
+  ],
+  "type_2_size": [
+    8,
+    12
+  ],
+  "type_3_size": [
+    8,
+    8
+  ],
+  "type_4_size": [
+    8,
+    12
+  ]
+}

ntu120-xsub-joint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac3b76a995cd9faa45bf184a1625c3730f590bd41f62acc340bc8105fc36ede3
+size 14556284

ntu60-inter-xsub-joint/README.md

@@ -0,0 +1,18 @@
+---
+library_name: skateformer
+license: mit
+pipeline_tag: video-classification
+tags:
+- action-recognition
+- eccv2024
+- model_hub_mixin
+- pytorch
+- pytorch_model_hub_mixin
+- skeleton-action-recognition
+- transformer
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Code: https://github.com/KAIST-VICLab/SkateFormer
+- Paper: https://huggingface.co/papers/2403.09508
+- Docs: https://kaist-viclab.github.io/SkateFormer_site/

ntu60-inter-xsub-joint/config.json

@@ -0,0 +1,59 @@
+{
+  "attn_drop": 0.5,
+  "channels": [
+    96,
+    192,
+    192,
+    192
+  ],
+  "depths": [
+    2,
+    2,
+    2,
+    2
+  ],
+  "drop": 0.0,
+  "drop_path": 0.2,
+  "embed_dim": 96,
+  "global_pool": "avg",
+  "head_drop": 0.0,
+  "id2label": {
+    "0": "punching/slapping other person",
+    "1": "kicking other person",
+    "2": "pushing other person",
+    "3": "pat on back of other person",
+    "4": "point finger at the other person",
+    "5": "hugging other person",
+    "6": "giving something to other person",
+    "7": "touch other person's pocket",
+    "8": "handshaking",
+    "9": "walking towards each other",
+    "10": "walking apart from each other"
+  },
+  "in_channels": 3,
+  "index_t": true,
+  "kernel_size": 7,
+  "mlp_ratio": 4.0,
+  "num_classes": 11,
+  "num_frames": 64,
+  "num_heads": 32,
+  "num_people": 2,
+  "num_points": 24,
+  "rel": true,
+  "type_1_size": [
+    8,
+    8
+  ],
+  "type_2_size": [
+    8,
+    12
+  ],
+  "type_3_size": [
+    8,
+    8
+  ],
+  "type_4_size": [
+    8,
+    12
+  ]
+}

ntu60-inter-xsub-joint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3ad2f34a6c7c4e28de7651b7f9f4f1c856f2b6523fa68a8bef9f661b08ad49a
+size 14472120

ntu60-inter-xview-joint/README.md

@@ -0,0 +1,18 @@
+---
+library_name: skateformer
+license: mit
+pipeline_tag: video-classification
+tags:
+- action-recognition
+- eccv2024
+- model_hub_mixin
+- pytorch
+- pytorch_model_hub_mixin
+- skeleton-action-recognition
+- transformer
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Code: https://github.com/KAIST-VICLab/SkateFormer
+- Paper: https://huggingface.co/papers/2403.09508
+- Docs: https://kaist-viclab.github.io/SkateFormer_site/

ntu60-inter-xview-joint/config.json

@@ -0,0 +1,59 @@
+{
+  "attn_drop": 0.5,
+  "channels": [
+    96,
+    192,
+    192,
+    192
+  ],
+  "depths": [
+    2,
+    2,
+    2,
+    2
+  ],
+  "drop": 0.0,
+  "drop_path": 0.2,
+  "embed_dim": 96,
+  "global_pool": "avg",
+  "head_drop": 0.0,
+  "id2label": {
+    "0": "punching/slapping other person",
+    "1": "kicking other person",
+    "2": "pushing other person",
+    "3": "pat on back of other person",
+    "4": "point finger at the other person",
+    "5": "hugging other person",
+    "6": "giving something to other person",
+    "7": "touch other person's pocket",
+    "8": "handshaking",
+    "9": "walking towards each other",
+    "10": "walking apart from each other"
+  },
+  "in_channels": 3,
+  "index_t": true,
+  "kernel_size": 7,
+  "mlp_ratio": 4.0,
+  "num_classes": 11,
+  "num_frames": 64,
+  "num_heads": 32,
+  "num_people": 2,
+  "num_points": 24,
+  "rel": true,
+  "type_1_size": [
+    8,
+    8
+  ],
+  "type_2_size": [
+    8,
+    12
+  ],
+  "type_3_size": [
+    8,
+    8
+  ],
+  "type_4_size": [
+    8,
+    12
+  ]
+}

ntu60-inter-xview-joint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93187c3589ec32025fbf8e21ed51e7ff7bd3c5155afaa65232bc3bde1d72759a
+size 14472120

ntu60-xsub-bone/README.md

@@ -0,0 +1,18 @@
+---
+library_name: skateformer
+license: mit
+pipeline_tag: video-classification
+tags:
+- action-recognition
+- eccv2024
+- model_hub_mixin
+- pytorch
+- pytorch_model_hub_mixin
+- skeleton-action-recognition
+- transformer
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Code: https://github.com/KAIST-VICLab/SkateFormer
+- Paper: https://huggingface.co/papers/2403.09508
+- Docs: https://kaist-viclab.github.io/SkateFormer_site/

ntu60-xsub-bone/config.json

@@ -0,0 +1,108 @@
+{
+  "attn_drop": 0.5,
+  "channels": [
+    96,
+    192,
+    192,
+    192
+  ],
+  "depths": [
+    2,
+    2,
+    2,
+    2
+  ],
+  "drop": 0.0,
+  "drop_path": 0.2,
+  "embed_dim": 96,
+  "global_pool": "avg",
+  "head_drop": 0.0,
+  "id2label": {
+    "0": "drink water",
+    "1": "eat meal/snack",
+    "2": "brushing teeth",
+    "3": "brushing hair",
+    "4": "drop",
+    "5": "pickup",
+    "6": "throw",
+    "7": "sitting down",
+    "8": "standing up (from sitting position)",
+    "9": "clapping",
+    "10": "reading",
+    "11": "writing",
+    "12": "tear up paper",
+    "13": "wear jacket",
+    "14": "take off jacket",
+    "15": "wear a shoe",
+    "16": "take off a shoe",
+    "17": "wear on glasses",
+    "18": "take off glasses",
+    "19": "put on a hat/cap",
+    "20": "take off a hat/cap",
+    "21": "cheer up",
+    "22": "hand waving",
+    "23": "kicking something",
+    "24": "reach into pocket",
+    "25": "hopping (one foot jumping)",
+    "26": "jump up",
+    "27": "make a phone call/answer phone",
+    "28": "playing with phone/tablet",
+    "29": "typing on a keyboard",
+    "30": "pointing to something with finger",
+    "31": "taking a selfie",
+    "32": "check time (from watch)",
+    "33": "rub two hands together",
+    "34": "nod head/bow",
+    "35": "shake head",
+    "36": "wipe face",
+    "37": "salute",
+    "38": "put the palms together",
+    "39": "cross hands in front (say stop)",
+    "40": "sneeze/cough",
+    "41": "staggering",
+    "42": "falling",
+    "43": "touch head (headache)",
+    "44": "touch chest (stomachache/heart pain)",
+    "45": "touch back (backache)",
+    "46": "touch neck (neckache)",
+    "47": "nausea or vomiting condition",
+    "48": "use a fan (with hand or paper)/feeling warm",
+    "49": "punching/slapping other person",
+    "50": "kicking other person",
+    "51": "pushing other person",
+    "52": "pat on back of other person",
+    "53": "point finger at the other person",
+    "54": "hugging other person",
+    "55": "giving something to other person",
+    "56": "touch other person's pocket",
+    "57": "handshaking",
+    "58": "walking towards each other",
+    "59": "walking apart from each other"
+  },
+  "in_channels": 3,
+  "index_t": true,
+  "kernel_size": 7,
+  "mlp_ratio": 4.0,
+  "num_classes": 60,
+  "num_frames": 64,
+  "num_heads": 32,
+  "num_people": 2,
+  "num_points": 24,
+  "rel": true,
+  "type_1_size": [
+    8,
+    8
+  ],
+  "type_2_size": [
+    8,
+    12
+  ],
+  "type_3_size": [
+    8,
+    8
+  ],
+  "type_4_size": [
+    8,
+    12
+  ]
+}

ntu60-xsub-bone/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f12dcd3b4a343bcc353b73d94f828263b89c6fd595d0566cf20c7d883435fcfe
+size 14509956

ntu60-xsub-joint/README.md

@@ -0,0 +1,18 @@
+---
+library_name: skateformer
+license: mit
+pipeline_tag: video-classification
+tags:
+- action-recognition
+- eccv2024
+- model_hub_mixin
+- pytorch
+- pytorch_model_hub_mixin
+- skeleton-action-recognition
+- transformer
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Code: https://github.com/KAIST-VICLab/SkateFormer
+- Paper: https://huggingface.co/papers/2403.09508
+- Docs: https://kaist-viclab.github.io/SkateFormer_site/

ntu60-xsub-joint/config.json

@@ -0,0 +1,108 @@
+{
+  "attn_drop": 0.5,
+  "channels": [
+    96,
+    192,
+    192,
+    192
+  ],
+  "depths": [
+    2,
+    2,
+    2,
+    2
+  ],
+  "drop": 0.0,
+  "drop_path": 0.2,
+  "embed_dim": 96,
+  "global_pool": "avg",
+  "head_drop": 0.0,
+  "id2label": {
+    "0": "drink water",
+    "1": "eat meal/snack",
+    "2": "brushing teeth",
+    "3": "brushing hair",
+    "4": "drop",
+    "5": "pickup",
+    "6": "throw",
+    "7": "sitting down",
+    "8": "standing up (from sitting position)",
+    "9": "clapping",
+    "10": "reading",
+    "11": "writing",
+    "12": "tear up paper",
+    "13": "wear jacket",
+    "14": "take off jacket",
+    "15": "wear a shoe",
+    "16": "take off a shoe",
+    "17": "wear on glasses",
+    "18": "take off glasses",
+    "19": "put on a hat/cap",
+    "20": "take off a hat/cap",
+    "21": "cheer up",
+    "22": "hand waving",
+    "23": "kicking something",
+    "24": "reach into pocket",
+    "25": "hopping (one foot jumping)",
+    "26": "jump up",
+    "27": "make a phone call/answer phone",
+    "28": "playing with phone/tablet",
+    "29": "typing on a keyboard",
+    "30": "pointing to something with finger",
+    "31": "taking a selfie",
+    "32": "check time (from watch)",
+    "33": "rub two hands together",
+    "34": "nod head/bow",
+    "35": "shake head",
+    "36": "wipe face",
+    "37": "salute",
+    "38": "put the palms together",
+    "39": "cross hands in front (say stop)",
+    "40": "sneeze/cough",
+    "41": "staggering",
+    "42": "falling",
+    "43": "touch head (headache)",
+    "44": "touch chest (stomachache/heart pain)",
+    "45": "touch back (backache)",
+    "46": "touch neck (neckache)",
+    "47": "nausea or vomiting condition",
+    "48": "use a fan (with hand or paper)/feeling warm",
+    "49": "punching/slapping other person",
+    "50": "kicking other person",
+    "51": "pushing other person",
+    "52": "pat on back of other person",
+    "53": "point finger at the other person",
+    "54": "hugging other person",
+    "55": "giving something to other person",
+    "56": "touch other person's pocket",
+    "57": "handshaking",
+    "58": "walking towards each other",
+    "59": "walking apart from each other"
+  },
+  "in_channels": 3,
+  "index_t": true,
+  "kernel_size": 7,
+  "mlp_ratio": 4.0,
+  "num_classes": 60,
+  "num_frames": 64,
+  "num_heads": 32,
+  "num_people": 2,
+  "num_points": 24,
+  "rel": true,
+  "type_1_size": [
+    8,
+    8
+  ],
+  "type_2_size": [
+    8,
+    12
+  ],
+  "type_3_size": [
+    8,
+    8
+  ],
+  "type_4_size": [
+    8,
+    12
+  ]
+}

ntu60-xsub-joint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53642858157ed03208f6511e8eb014e10d6a810cb468e09e9a9fdc3aff5c368f
+size 14509956

ntu60-xview-bone/README.md

@@ -0,0 +1,18 @@
+---
+library_name: skateformer
+license: mit
+pipeline_tag: video-classification
+tags:
+- action-recognition
+- eccv2024
+- model_hub_mixin
+- pytorch
+- pytorch_model_hub_mixin
+- skeleton-action-recognition
+- transformer
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Code: https://github.com/KAIST-VICLab/SkateFormer
+- Paper: https://huggingface.co/papers/2403.09508
+- Docs: https://kaist-viclab.github.io/SkateFormer_site/

ntu60-xview-bone/config.json

@@ -0,0 +1,108 @@
+{
+  "attn_drop": 0.5,
+  "channels": [
+    96,
+    192,
+    192,
+    192
+  ],
+  "depths": [
+    2,
+    2,
+    2,
+    2
+  ],
+  "drop": 0.0,
+  "drop_path": 0.2,
+  "embed_dim": 96,
+  "global_pool": "avg",
+  "head_drop": 0.0,
+  "id2label": {
+    "0": "drink water",
+    "1": "eat meal/snack",
+    "2": "brushing teeth",
+    "3": "brushing hair",
+    "4": "drop",
+    "5": "pickup",
+    "6": "throw",
+    "7": "sitting down",
+    "8": "standing up (from sitting position)",
+    "9": "clapping",
+    "10": "reading",
+    "11": "writing",
+    "12": "tear up paper",
+    "13": "wear jacket",
+    "14": "take off jacket",
+    "15": "wear a shoe",
+    "16": "take off a shoe",
+    "17": "wear on glasses",
+    "18": "take off glasses",
+    "19": "put on a hat/cap",
+    "20": "take off a hat/cap",
+    "21": "cheer up",
+    "22": "hand waving",
+    "23": "kicking something",
+    "24": "reach into pocket",
+    "25": "hopping (one foot jumping)",
+    "26": "jump up",
+    "27": "make a phone call/answer phone",
+    "28": "playing with phone/tablet",
+    "29": "typing on a keyboard",
+    "30": "pointing to something with finger",
+    "31": "taking a selfie",
+    "32": "check time (from watch)",
+    "33": "rub two hands together",
+    "34": "nod head/bow",
+    "35": "shake head",
+    "36": "wipe face",
+    "37": "salute",
+    "38": "put the palms together",
+    "39": "cross hands in front (say stop)",
+    "40": "sneeze/cough",
+    "41": "staggering",
+    "42": "falling",
+    "43": "touch head (headache)",
+    "44": "touch chest (stomachache/heart pain)",
+    "45": "touch back (backache)",
+    "46": "touch neck (neckache)",
+    "47": "nausea or vomiting condition",
+    "48": "use a fan (with hand or paper)/feeling warm",
+    "49": "punching/slapping other person",
+    "50": "kicking other person",
+    "51": "pushing other person",
+    "52": "pat on back of other person",
+    "53": "point finger at the other person",
+    "54": "hugging other person",
+    "55": "giving something to other person",
+    "56": "touch other person's pocket",
+    "57": "handshaking",
+    "58": "walking towards each other",
+    "59": "walking apart from each other"
+  },
+  "in_channels": 3,
+  "index_t": true,
+  "kernel_size": 7,
+  "mlp_ratio": 4.0,
+  "num_classes": 60,
+  "num_frames": 64,
+  "num_heads": 32,
+  "num_people": 2,
+  "num_points": 24,
+  "rel": true,
+  "type_1_size": [
+    8,
+    8
+  ],
+  "type_2_size": [
+    8,
+    12
+  ],
+  "type_3_size": [
+    8,
+    8
+  ],
+  "type_4_size": [
+    8,
+    12
+  ]
+}

ntu60-xview-bone/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bfa161bcf8b3266d8cf7592b5073afe933fee7caeb377c402719d712982c7e9
+size 14509956

ntu60-xview-joint/README.md

@@ -0,0 +1,18 @@
+---
+library_name: skateformer
+license: mit
+pipeline_tag: video-classification
+tags:
+- action-recognition
+- eccv2024
+- model_hub_mixin
+- pytorch
+- pytorch_model_hub_mixin
+- skeleton-action-recognition
+- transformer
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Code: https://github.com/KAIST-VICLab/SkateFormer
+- Paper: https://huggingface.co/papers/2403.09508
+- Docs: https://kaist-viclab.github.io/SkateFormer_site/

ntu60-xview-joint/config.json

@@ -0,0 +1,108 @@
+{
+  "attn_drop": 0.5,
+  "channels": [
+    96,
+    192,
+    192,
+    192
+  ],
+  "depths": [
+    2,
+    2,
+    2,
+    2
+  ],
+  "drop": 0.0,
+  "drop_path": 0.2,
+  "embed_dim": 96,
+  "global_pool": "avg",
+  "head_drop": 0.0,
+  "id2label": {
+    "0": "drink water",
+    "1": "eat meal/snack",
+    "2": "brushing teeth",
+    "3": "brushing hair",
+    "4": "drop",
+    "5": "pickup",
+    "6": "throw",
+    "7": "sitting down",
+    "8": "standing up (from sitting position)",
+    "9": "clapping",
+    "10": "reading",
+    "11": "writing",
+    "12": "tear up paper",
+    "13": "wear jacket",
+    "14": "take off jacket",
+    "15": "wear a shoe",
+    "16": "take off a shoe",
+    "17": "wear on glasses",
+    "18": "take off glasses",
+    "19": "put on a hat/cap",
+    "20": "take off a hat/cap",
+    "21": "cheer up",
+    "22": "hand waving",
+    "23": "kicking something",
+    "24": "reach into pocket",
+    "25": "hopping (one foot jumping)",
+    "26": "jump up",
+    "27": "make a phone call/answer phone",
+    "28": "playing with phone/tablet",
+    "29": "typing on a keyboard",
+    "30": "pointing to something with finger",
+    "31": "taking a selfie",
+    "32": "check time (from watch)",
+    "33": "rub two hands together",
+    "34": "nod head/bow",
+    "35": "shake head",
+    "36": "wipe face",
+    "37": "salute",
+    "38": "put the palms together",
+    "39": "cross hands in front (say stop)",
+    "40": "sneeze/cough",
+    "41": "staggering",
+    "42": "falling",
+    "43": "touch head (headache)",
+    "44": "touch chest (stomachache/heart pain)",
+    "45": "touch back (backache)",
+    "46": "touch neck (neckache)",
+    "47": "nausea or vomiting condition",
+    "48": "use a fan (with hand or paper)/feeling warm",
+    "49": "punching/slapping other person",
+    "50": "kicking other person",
+    "51": "pushing other person",
+    "52": "pat on back of other person",
+    "53": "point finger at the other person",
+    "54": "hugging other person",
+    "55": "giving something to other person",
+    "56": "touch other person's pocket",
+    "57": "handshaking",
+    "58": "walking towards each other",
+    "59": "walking apart from each other"
+  },
+  "in_channels": 3,
+  "index_t": true,
+  "kernel_size": 7,
+  "mlp_ratio": 4.0,
+  "num_classes": 60,
+  "num_frames": 64,
+  "num_heads": 32,
+  "num_people": 2,
+  "num_points": 24,
+  "rel": true,
+  "type_1_size": [
+    8,
+    8
+  ],
+  "type_2_size": [
+    8,
+    12
+  ],
+  "type_3_size": [
+    8,
+    8
+  ],
+  "type_4_size": [
+    8,
+    12
+  ]
+}

ntu60-xview-joint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4c048f5931dd3ed6ee549b30075b0d56915b9763f18ddaf8957981970f0c05d
+size 14509956

nwucla-bone/README.md

@@ -0,0 +1,18 @@
+---
+library_name: skateformer
+license: mit
+pipeline_tag: video-classification
+tags:
+- action-recognition
+- eccv2024
+- model_hub_mixin
+- pytorch
+- pytorch_model_hub_mixin
+- skeleton-action-recognition
+- transformer
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Code: https://github.com/KAIST-VICLab/SkateFormer
+- Paper: https://huggingface.co/papers/2403.09508
+- Docs: https://kaist-viclab.github.io/SkateFormer_site/

nwucla-bone/config.json

@@ -0,0 +1,58 @@
+{
+  "attn_drop": 0.5,
+  "channels": [
+    96,
+    192,
+    192,
+    192
+  ],
+  "depths": [
+    2,
+    2,
+    2,
+    2
+  ],
+  "drop": 0.0,
+  "drop_path": 0.2,
+  "embed_dim": 96,
+  "global_pool": "avg",
+  "head_drop": 0.0,
+  "id2label": {
+    "0": "pick up with one hand",
+    "1": "pick up with two hands",
+    "2": "drop trash",
+    "3": "walk around",
+    "4": "sit down",
+    "5": "stand up",
+    "6": "donning",
+    "7": "doffing",
+    "8": "throw",
+    "9": "carry"
+  },
+  "in_channels": 3,
+  "index_t": true,
+  "kernel_size": 7,
+  "mlp_ratio": 1.0,
+  "num_classes": 10,
+  "num_frames": 64,
+  "num_heads": 32,
+  "num_people": 1,
+  "num_points": 20,
+  "rel": true,
+  "type_1_size": [
+    8,
+    4
+  ],
+  "type_2_size": [
+    8,
+    5
+  ],
+  "type_3_size": [
+    8,
+    4
+  ],
+  "type_4_size": [
+    8,
+    5
+  ]
+}

nwucla-bone/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab26b2a3168890f965dfe13f7c182721b193a8283f0b70624a0d872eec3e3e9d
+size 7749132

nwucla-joint/README.md

@@ -0,0 +1,18 @@
+---
+library_name: skateformer
+license: mit
+pipeline_tag: video-classification
+tags:
+- action-recognition
+- eccv2024
+- model_hub_mixin
+- pytorch
+- pytorch_model_hub_mixin
+- skeleton-action-recognition
+- transformer
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Code: https://github.com/KAIST-VICLab/SkateFormer
+- Paper: https://huggingface.co/papers/2403.09508
+- Docs: https://kaist-viclab.github.io/SkateFormer_site/

nwucla-joint/config.json

@@ -0,0 +1,58 @@
+{
+  "attn_drop": 0.5,
+  "channels": [
+    96,
+    192,
+    192,
+    192
+  ],
+  "depths": [
+    2,
+    2,
+    2,
+    2
+  ],
+  "drop": 0.0,
+  "drop_path": 0.2,
+  "embed_dim": 96,
+  "global_pool": "avg",
+  "head_drop": 0.0,
+  "id2label": {
+    "0": "pick up with one hand",
+    "1": "pick up with two hands",
+    "2": "drop trash",
+    "3": "walk around",
+    "4": "sit down",
+    "5": "stand up",
+    "6": "donning",
+    "7": "doffing",
+    "8": "throw",
+    "9": "carry"
+  },
+  "in_channels": 3,
+  "index_t": true,
+  "kernel_size": 7,
+  "mlp_ratio": 1.0,
+  "num_classes": 10,
+  "num_frames": 64,
+  "num_heads": 32,
+  "num_people": 1,
+  "num_points": 20,
+  "rel": true,
+  "type_1_size": [
+    8,
+    4
+  ],
+  "type_2_size": [
+    8,
+    5
+  ],
+  "type_3_size": [
+    8,
+    4
+  ],
+  "type_4_size": [
+    8,
+    5
+  ]
+}

nwucla-joint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da9e51e10468a0e74a0243bf9c0b0ead68bc6d140514b3e091f1037418912049
+size 7749132