Static or Dynamic: Towards Query-Adaptive Token Selection for Video Question Answering (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to compress video inputs ignore the importance of static and dynamic information in long videos, leading to inefficient token usage within limited budgets. |
| Approach: | They propose a token selection strategy that adaptively adjusts static and dynamic information based on question requirements. |
| Outcome: | The proposed method achieves performance improvements (up to 5.8%) on multiple video question answering benchmarks. |
Similar Papers
VideoQA-TA: Temporal-Aware Multi-Modal Video Question Answering (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods for video question answering align visual or textual features directly with large language models, limiting the deep semantic association between modalities and hindering a comprehensive understanding of interactions within spatial and temporal contexts. |
| Approach: | They propose a temporal-aware framework for multi-modal video question answering that aligns videos and questions at fine-grained levels. |
| Outcome: | The proposed framework improves reasoning ability and accuracy of videoQA by aligning videos and questions at fine-grained levels. |
Dense-Caption Matching and Frame-Selection Gating for Temporal Localization in VideoQA (2020.acl-main)
Copied to clipboard
| Challenge: | Recent years have witnessed a paradigm shift in the way we get our information, and a lot of it. |
| Approach: | They propose a video question answering model which integrates multi-modal input sources and finds temporally relevant information to answer questions. |
| Outcome: | The proposed model outperforms the state-of-the-art on a TVQA dataset. |
D-CoDe: Scaling Image-Pretrained VLMs to Video via Dynamic Compression and Question Decomposition (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing training-free adaptation frameworks for video large language models are limited by the scarcity of high-quality video-text data. |
| Approach: | They propose a training-free adaptation framework that incorporates dynamic compression and question decomposition to address perception bottleneck and token overload. |
| Outcome: | The proposed framework improves video understanding across various benchmarks and on long-video benchmarks. |
Self-Adaptive Sampling for Accurate Video Question Answering on Image Text Models (2024.findings-naacl)
Copied to clipboard
| Challenge: | Image–text models (ITMs) are the prevalent architecture to solve video question–answering tasks, which requires only a few input frames to save huge computational cost compared to video–language models. |
| Approach: | They propose a sampling method based on question–frame correlation that is efficient for the few-frame situations. |
| Outcome: | The proposed method can boost the performance of image–text pretrained models and have a wide application scenario in terms of model architectures and dataset types. |
Vista-LLM: Decoupled Query-Guided Visual Token Pruning for Efficient Long-Video Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Long-video understanding is bottlenecked by the high cost of processing massive visual tokens. |
| Approach: | They propose a decoupled framework for query-guided visual token pruning . their method reduces visual tokens by 90% and accelerates inference by 98% . |
| Outcome: | The proposed framework reduces visual tokens by 90% and accelerates inference while retaining over 98% of baseline performance on average. |
Dynamic Feature Selection with Attention in Incremental Parsing (C18-1)
Copied to clipboard
| Challenge: | Currently, incremental transition-based parsers require that all inputs are visible from the beginning to extract good features from a limited local context. |
| Approach: | They propose a technique to maximize local features with an attention mechanism which works as context- dependent dynamic feature selection. |
| Outcome: | The proposed technique can extract features from a limited local context and is able to perform multilingual experiments and demon strate on local ambiguous points. |
PruneVid: Visual Token Pruning for Efficient Video Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to video token pruning face significant computational challenges due to the redundancy inherent in video data. |
| Approach: | They propose a training-free visual token pruning method that reduces the redundancy inherent in video data and leverages LLMs’ inherent ability to selectively prune visual tokens irrelevant to specific queries. |
| Outcome: | The proposed method can prune over 80% of tokens while maintaining competitive performance when combined with different video LLMs. |
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Experimental results show that TESTA reduces the number of visual tokens by 75% and thus accelerates video encoding. |
| Approach: | They propose a method to condense video semantics by aggregating similar frames and patches within each frame. |
| Outcome: | The proposed method reduces visual tokens by 75% and accelerates video encoding. |
Towards Parameter-Efficient Integration of Pre-Trained Language Models In Temporal Video Grounding (2023.findings-acl)
Copied to clipboard
Erica Kido Shimomoto, Edison Marrese-Taylor, Hiroya Takamura, Ichiro Kobayashi, Hideki Nakayama, Yusuke Miyao
| Challenge: | Recent studies have improved query inputs with pre-trained language models, but the effects of this integration are unclear. |
| Approach: | They propose to integrate query sentences with pre-trained language models to train TVG models. |
| Outcome: | The proposed model integrates query sentences with pre-trained language models at cost of more expensive training. |
RAP: Efficient Text-Video Retrieval with Sparse-and-Correlated Adapter (2024.findings-acl)
Copied to clipboard
Meng Cao, Haoran Tang, Jinfa Huang, Peng Jin, Can Zhang, Ruyang Liu, Long Chen, Xiaodan Liang, Li Yuan, Ge Li
| Challenge: | Text-Video Retrieval (TVR) aims to align relevant video content with natural language queries. |
| Approach: | They propose to conduct efficient text-video Retrieval with a salient-and-correlated AdaPter . they propose a low-rank modulation module to refine per-image features from frozen CLIP backbone . |
| Outcome: | Experiments on four TVR datasets show that the proposed method performs better than other methods. |