wudq commited on
Commit
0ab378c
路
verified 路
1 Parent(s): cb36709

Add comprehensive EmObserver model card

Browse files
Files changed (1) hide show
  1. README.md +10 -2
README.md CHANGED
@@ -82,6 +82,7 @@ The model accepts one or more images with a natural-language question and produc
82
  | Resource | Description | Link |
83
  | --- | --- | --- |
84
  | Paper | MVEI & EmObserver | [arXiv:2607.21061](https://arxiv.org/abs/2607.21061) |
 
85
  | Official code | Inference, evaluation, and four-stage training | [wdqqdw/EmObserver](https://github.com/wdqqdw/EmObserver) |
86
  | Expanded release | Benchmarks, images, predictions, and training data | [wudq/MVEI_PLUS](https://huggingface.co/datasets/wudq/MVEI_PLUS) |
87
  | EmObserver results | Released predictions and metric summaries | [MVEI_PLUS/baselines/Qwen3-VL-EMOBSERVER](https://huggingface.co/datasets/wudq/MVEI_PLUS/tree/main/baselines/Qwen3-VL-EMOBSERVER) |
@@ -300,7 +301,7 @@ The checkpoint is released under the Apache 2.0 license, following its [Qwen3-VL
300
 
301
  ## 馃摑 Citation
302
 
303
- If you use EmObserver, MVEI, or the expanded release, please cite:
304
 
305
  ```bibtex
306
  @article{wu2026mvei_emobserver,
@@ -309,5 +310,12 @@ If you use EmObserver, MVEI, or the expanded release, please cite:
309
  journal = {arXiv preprint arXiv:2607.21061},
310
  year = {2026}
311
  }
312
- ```
313
 
 
 
 
 
 
 
 
 
 
82
  | Resource | Description | Link |
83
  | --- | --- | --- |
84
  | Paper | MVEI & EmObserver | [arXiv:2607.21061](https://arxiv.org/abs/2607.21061) |
85
+ | Original paper (ICLR 2026) | Customizing Visual Emotion Evaluation for MLLMs | [OpenReview](https://openreview.net/forum?id=dQTSXWqZws) 路 [arXiv:2509.21950](https://arxiv.org/abs/2509.21950) |
86
  | Official code | Inference, evaluation, and four-stage training | [wdqqdw/EmObserver](https://github.com/wdqqdw/EmObserver) |
87
  | Expanded release | Benchmarks, images, predictions, and training data | [wudq/MVEI_PLUS](https://huggingface.co/datasets/wudq/MVEI_PLUS) |
88
  | EmObserver results | Released predictions and metric summaries | [MVEI_PLUS/baselines/Qwen3-VL-EMOBSERVER](https://huggingface.co/datasets/wudq/MVEI_PLUS/tree/main/baselines/Qwen3-VL-EMOBSERVER) |
 
301
 
302
  ## 馃摑 Citation
303
 
304
+ If you use EmObserver or the expanded training and evaluation release, please cite the EmObserver paper below. When using the MVEI benchmark, dataset, or Emotion Statement Judgement formulation, please also cite the original ICLR 2026 paper.
305
 
306
  ```bibtex
307
  @article{wu2026mvei_emobserver,
 
310
  journal = {arXiv preprint arXiv:2607.21061},
311
  year = {2026}
312
  }
 
313
 
314
+ @inproceedings{wu2026customizing,
315
+ title = {Customizing Visual Emotion Evaluation for MLLMs: An Open-vocabulary, Multifaceted, and Scalable Approach},
316
+ author = {Wu, Daiqing and Yang, Dongbao and Zhao, Sicheng and Ma, Can and Zhou, Yu},
317
+ booktitle = {International Conference on Learning Representations},
318
+ year = {2026},
319
+ url = {https://openreview.net/forum?id=dQTSXWqZws}
320
+ }
321
+ ```