HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understanding
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909592175247360 |
|---|---|
| author | Azad, Shehreen Vineet, Vibhav Rawat, Yogesh Singh |
| author_facet | Azad, Shehreen Vineet, Vibhav Rawat, Yogesh Singh |
| contents | Despite advancements in multimodal large language models (MLLMs), current approaches struggle in medium-to-long video understanding due to frame and context length limitations. As a result, these models often depend on frame sampling, which risks missing key information over time and lacks task-specific relevance. To address these challenges, we introduce HierarQ, a task-aware hierarchical Q-Former based framework that sequentially processes frames to bypass the need for frame sampling, while avoiding LLM's context length limitations. We introduce a lightweight two-stream language-guided feature modulator to incorporate task awareness in video understanding, with the entity stream capturing frame-level object information within a short context and the scene stream identifying their broader interactions over longer period of time. Each stream is supported by dedicated memory banks which enables our proposed Hierachical Querying transformer (HierarQ) to effectively capture short and long-term context. Extensive evaluations on 10 video benchmarks across video understanding, question answering, and captioning tasks demonstrate HierarQ's state-of-the-art performance across most datasets, proving its robustness and efficiency for comprehensive video analysis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_08585 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understanding Azad, Shehreen Vineet, Vibhav Rawat, Yogesh Singh Computer Vision and Pattern Recognition Despite advancements in multimodal large language models (MLLMs), current approaches struggle in medium-to-long video understanding due to frame and context length limitations. As a result, these models often depend on frame sampling, which risks missing key information over time and lacks task-specific relevance. To address these challenges, we introduce HierarQ, a task-aware hierarchical Q-Former based framework that sequentially processes frames to bypass the need for frame sampling, while avoiding LLM's context length limitations. We introduce a lightweight two-stream language-guided feature modulator to incorporate task awareness in video understanding, with the entity stream capturing frame-level object information within a short context and the scene stream identifying their broader interactions over longer period of time. Each stream is supported by dedicated memory banks which enables our proposed Hierachical Querying transformer (HierarQ) to effectively capture short and long-term context. Extensive evaluations on 10 video benchmarks across video understanding, question answering, and captioning tasks demonstrate HierarQ's state-of-the-art performance across most datasets, proving its robustness and efficiency for comprehensive video analysis. |
| title | HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understanding |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.08585 |