MIST: Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answering

• URL: http://arxiv.org/abs/2212.09522v1
• Date: Mon, 19 Dec 2022 15:05:40 GMT
• Title: MIST: Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answering
• Authors: Difei Gao, Luowei Zhou, Lei Ji, Linchao Zhu, Yi Yang, Mike Zheng Shou
• Abstract summary: We introduce a new model named Multi-modal Iterative Spatial-temporal Transformer (MIST) to better adapt pre-trained models for long-form VideoQA. MIST decomposes traditional dense spatial-temporal self-attention into cascaded segment and region selection modules. Visual concepts at different granularities are then processed efficiently through an attention module.
• Score: 73.61182342844639
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: To build Video Question Answering (VideoQA) systems capable of assisting humans in daily activities, seeking answers from long-form videos with diverse and complex events is a must. Existing multi-modal VQA models achieve promising performance on images or short video clips, especially with the recent success of large-scale multi-modal pre-training. However, when extending these methods to long-form videos, new challenges arise. On the one hand, using a dense video sampling strategy is computationally prohibitive. On the other hand, methods relying on sparse sampling struggle in scenarios where multi-event and multi-granularity visual reasoning are required. In this work, we introduce a new model named Multi-modal Iterative Spatial-temporal Transformer (MIST) to better adapt pre-trained models for long-form VideoQA. Specifically, MIST decomposes traditional dense spatial-temporal self-attention into cascaded segment and region selection modules that adaptively select frames and image regions that are closely relevant to the question itself. Visual concepts at different granularities are then processed efficiently through an attention module. In addition, MIST iteratively conducts selection and attention over multiple layers to support reasoning over multiple events. The experimental results on four VideoQA datasets, including AGQA, NExT-QA, STAR, and Env-QA, show that MIST achieves state-of-the-art performance and is superior at computation efficiency and interpretability.

Related papers

• Free Video-LLM: Prompt-guided Visual Perception for Efficient Training-free Video LLMs [56.040198387038025]
  We present a novel prompt-guided visual perception framework (abbreviated as Free Video-LLM) for efficient inference of training-free video LLMs. Our method effectively reduces the number of visual tokens while maintaining high performance across multiple video question-answering benchmarks.
  arXiv  Detail & Related papers  (2024-10-14T12:35:12Z)
• Multi-granularity Contrastive Cross-modal Collaborative Generation for End-to-End Long-term Video Question Answering [53.39158264785098]
  Long-term Video Question Answering (VideoQA) is a challenging vision-and-language bridging task. We present an entirely end-to-end solution for VideoQA: Multi-granularity Contrastive cross-modal collaborative Generation model.
  arXiv  Detail & Related papers  (2024-10-12T06:21:58Z)
• Top-down Activity Representation Learning for Video Question Answering [4.236280446793381]
  Capturing complex hierarchical human activities is crucial for achieving high-performance video question answering (VideoQA) We convert long-term video sequences into a spatial image domain and finetune the multimodal model LLaVA for the VideoQA task. Our approach achieves competitive performance on the STAR task, in particular, with a 78.4% accuracy score, exceeding the current state-of-the-art score by 2.8 points on the NExTQA task.
  arXiv  Detail & Related papers  (2024-09-12T04:43:27Z)
• Grounded Multi-Hop VideoQA in Long-Form Egocentric Videos [35.974750867072345]
  This paper considers the problem of Multi-Hop Video Question Answering (MH-VidQA) in long-form egocentric videos. We develop an automated pipeline to create multi-hop question-answering pairs with associated temporal evidence. We then propose a novel architecture, termed as Grounding Scattered Evidence with Large Language Model (GeLM), that enhances multi-modal large language models.
  arXiv  Detail & Related papers  (2024-08-26T17:58:47Z)
• MoVQA: A Benchmark of Versatile Question-Answering for Long-Form Movie Understanding [69.04413943858584]
  We introduce MoVQA, a long-form movie question-answering dataset. We also benchmark to assess the diverse cognitive capabilities of multimodal systems.
  arXiv  Detail & Related papers  (2023-12-08T03:33:38Z)
• MuLTI: Efficient Video-and-Language Understanding with Text-Guided MultiWay-Sampler and Multiple Choice Modeling [7.737755720567113]
  This paper proposes MuLTI, a highly accurate and efficient video-and-language understanding model. We design a Text-Guided MultiWay-Sampler based on adapt-pooling residual mapping and self-attention modules. We also propose a new pretraining task named Multiple Choice Modeling.
  arXiv  Detail & Related papers  (2023-03-10T05:22:39Z)
• DeepQAMVS: Query-Aware Hierarchical Pointer Networks for Multi-Video Summarization [127.16984421969529]
  We introduce a novel Query-Aware Hierarchical Pointer Network for Multi-Video Summarization, termed DeepQAMVS. DeepQAMVS is trained with reinforcement learning, incorporating rewards that capture representativeness, diversity, query-adaptability and temporal coherence. We achieve state-of-the-art results on the MVS1K dataset, with inference time scaling linearly with the number of input video frames.
  arXiv  Detail & Related papers  (2021-05-13T17:33:26Z)
• Frame-wise Cross-modal Matching for Video Moment Retrieval [32.68921139236391]
  Video moment retrieval targets at retrieving a moment in a video for a given language query. The challenges of this task include 1) the requirement of localizing the relevant moment in an untrimmed video, and 2) bridging the semantic gap between textual query and video contents. We propose an Attentive Cross-modal Relevance Matching model which predicts the temporal boundaries based on an interaction modeling.
  arXiv  Detail & Related papers  (2020-09-22T10:25:41Z)
• Dense-Caption Matching and Frame-Selection Gating for Temporal Localization in VideoQA [96.10612095576333]
  We propose a video question answering model which effectively integrates multi-modal input sources and finds the temporally relevant information to answer questions. Our model is also comprised of dual-level attention (word/object and frame level), multi-head self-cross-integration for different sources (video and dense captions), and which pass more relevant information to gates. We evaluate our model on the challenging TVQA dataset, where each of our model components provides significant gains, and our overall model outperforms the state-of-the-art by a large margin.
  arXiv  Detail & Related papers  (2020-05-13T16:35:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.