Improve model card: Add tags and links

#1
by nielsr HF Staff - opened
Files changed (1) hide show
  1. README.md +5 -0
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.