Improve model card: Add tags and links
#1
by
nielsr
HF Staff
- opened
README.md
CHANGED
|
@@ -1,9 +1,14 @@
|
|
| 1 |
---
|
| 2 |
license: cc-by-4.0
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
|
| 5 |
Welcome to **EmoCaliber**, an MLLM for reliable visual emotion comprehension.
|
| 6 |
|
|
|
|
|
|
|
|
|
|
| 7 |
Given an image, EmoCaliber is trained to produce structured affective reasoning following this pipeline: (1) identifying prominent visual elements in the image; (2) providing detailed descriptions of human subjects, if present; (3) describing contextual elements beyond the subjects; (4) discussing how these elements interact; and (5) deriving an emotional conclusion based on the preceding observations. The final emotion prediction integrates these visual cues. After outputting the prediction, EmoCaliber also emits a confidence score wrapped in a \<confidence\> tag, which reflects the model’s self-assessed certainty about its answer.
|
| 8 |
|
| 9 |
EmoCaliber is implemented based on Qwen2.5-VL-7B and can perform both inference and training in an identical manner.
|
|
|
|
| 1 |
---
|
| 2 |
license: cc-by-4.0
|
| 3 |
+
pipeline_tag: image-text-to-text
|
| 4 |
+
library_name: transformers
|
| 5 |
---
|
| 6 |
|
| 7 |
Welcome to **EmoCaliber**, an MLLM for reliable visual emotion comprehension.
|
| 8 |
|
| 9 |
+
**Paper:** [EmoCaliber: Advancing Reliable Visual Emotion Comprehension via Confidence Verbalization and Calibration](https://huggingface.co/papers/2512.15528)
|
| 10 |
+
**Code / Project Page:** [https://github.com/wdqqdw/EmoCaliber](https://github.com/wdqqdw/EmoCaliber)
|
| 11 |
+
|
| 12 |
Given an image, EmoCaliber is trained to produce structured affective reasoning following this pipeline: (1) identifying prominent visual elements in the image; (2) providing detailed descriptions of human subjects, if present; (3) describing contextual elements beyond the subjects; (4) discussing how these elements interact; and (5) deriving an emotional conclusion based on the preceding observations. The final emotion prediction integrates these visual cues. After outputting the prediction, EmoCaliber also emits a confidence score wrapped in a \<confidence\> tag, which reflects the model’s self-assessed certainty about its answer.
|
| 13 |
|
| 14 |
EmoCaliber is implemented based on Qwen2.5-VL-7B and can perform both inference and training in an identical manner.
|