Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2407.15046 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913439419465728 |
|---|---|
| author | Sagare, Shivprasad S, Hemachandran Sarabhai, Kinshuk Ullegaddi, Prashant SA, Rajeshkumar |
| author_facet | Sagare, Shivprasad S, Hemachandran Sarabhai, Kinshuk Ullegaddi, Prashant SA, Rajeshkumar |
| contents | Recent advances in multimodal LLMs, have led to several video-text models being proposed for critical video-related tasks. However, most of the previous works support visual input only, essentially muting the audio signal in the video. Few models that support both audio and visual input, are not explicitly trained on audio data. Hence, the effect of audio towards video understanding is largely unexplored. To this end, we propose a model architecture that handles audio-visual inputs explicitly. We train our model with both audio and visual data from a video instruction-tuning dataset. Comparison with vision-only baselines, and other audio-visual models showcase that training on audio data indeed leads to improved grounding of responses. For better evaluation of audio-visual models, we also release a human-annotated benchmark dataset, with audio-aware question-answer pairs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_15046 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Audio-visual training for improved grounding in video-text LLMs Sagare, Shivprasad S, Hemachandran Sarabhai, Kinshuk Ullegaddi, Prashant SA, Rajeshkumar Computer Vision and Pattern Recognition Computation and Language Multimedia Recent advances in multimodal LLMs, have led to several video-text models being proposed for critical video-related tasks. However, most of the previous works support visual input only, essentially muting the audio signal in the video. Few models that support both audio and visual input, are not explicitly trained on audio data. Hence, the effect of audio towards video understanding is largely unexplored. To this end, we propose a model architecture that handles audio-visual inputs explicitly. We train our model with both audio and visual data from a video instruction-tuning dataset. Comparison with vision-only baselines, and other audio-visual models showcase that training on audio data indeed leads to improved grounding of responses. For better evaluation of audio-visual models, we also release a human-annotated benchmark dataset, with audio-aware question-answer pairs. |
| title | Audio-visual training for improved grounding in video-text LLMs |
| topic | Computer Vision and Pattern Recognition Computation and Language Multimedia |
| url | https://arxiv.org/abs/2407.15046 |