Character Matters: Video Story Understanding with Character-Aware Relations

• URL: http://arxiv.org/abs/2005.08646v1
• Date: Sat, 9 May 2020 06:51:13 GMT
• Title: Character Matters: Video Story Understanding with Character-Aware Relations
• Authors: Shijie Geng, Ji Zhang, Zuohui Fu, Peng Gao, Hang Zhang, Gerard de Melo
• Abstract summary: Video Story Question Answering (VSQA) offers an effective way to benchmark higher-level comprehension abilities of a model. Current VSQA methods merely extract generic visual features from a scene. We propose a novel model that continuously refines character-aware relations.
• Score: 47.69347058141917
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Different from short videos and GIFs, video stories contain clear plots and lists of principal characters. Without identifying the connection between appearing people and character names, a model is not able to obtain a genuine understanding of the plots. Video Story Question Answering (VSQA) offers an effective way to benchmark higher-level comprehension abilities of a model. However, current VSQA methods merely extract generic visual features from a scene. With such an approach, they remain prone to learning just superficial correlations. In order to attain a genuine understanding of who did what to whom, we propose a novel model that continuously refines character-aware relations. This model specifically considers the characters in a video story, as well as the relations connecting different characters and objects. Based on these signals, our framework enables weakly-supervised face naming through multi-instance co-occurrence matching and supports high-level reasoning utilizing Transformer structures. We train and test our model on the six diverse TV shows in the TVQA dataset, which is by far the largest and only publicly available dataset for VSQA. We validate our proposed approach over TVQA dataset through extensive ablation study.

Related papers

• Answer, Assemble, Ace: Understanding How Transformers Answer Multiple Choice Questions [103.20281438405111]
  Multiple-choice question answering (MCQA) is a key competence of performant transformer language models. We employ vocabulary projection and activation patching methods to localize key hidden states that encode relevant information. We show that prediction of a specific answer symbol is causally attributed to a single middle layer, and specifically its multi-head self-attention mechanism.
  arXiv  Detail & Related papers  (2024-07-21T00:10:23Z)
• Can I Trust Your Answer? Visually Grounded Video Question Answering [88.11169242115416]
  We study visually grounded VideoQA in response to the emerging trends of utilizing pretraining techniques for video-language understanding. We construct NExT-GQA -- an extension of NExT-QA with 10.5$K$ temporal grounding labels tied to the original QA pairs.
  arXiv  Detail & Related papers  (2023-09-04T03:06:04Z)
• Keyword-Aware Relative Spatio-Temporal Graph Networks for Video Question Answering [16.502197578954917]
  graph-based methods for VideoQA usually ignore keywords in questions and employ a simple graph to aggregate features. We propose a Keyword-aware Relative Spatio-Temporal (KRST) graph network for VideoQA.
  arXiv  Detail & Related papers  (2023-07-25T04:41:32Z)
• Classification-Regression for Chart Comprehension [16.311371103939205]
  Chart question answering (CQA) is a task used for assessing chart comprehension. We propose a new model that jointly learns classification and regression. Our model's edge is particularly emphasized on questions with out-of-vocabulary answers.
  arXiv  Detail & Related papers  (2021-11-29T18:46:06Z)
• CLIP-It! Language-Guided Video Summarization [96.69415453447166]
  This work introduces CLIP-It, a single framework for addressing both generic and query-focused video summarization. We propose a language-guided multimodal transformer that learns to score frames in a video based on their importance relative to one another. Our model can be extended to the unsupervised setting by training without ground-truth supervision.
  arXiv  Detail & Related papers  (2021-07-01T17:59:27Z)
• VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning [82.09856883441044]
  Video understanding relies on perceiving the global content modeling its internal connections. We propose a block-wise strategy where we mask neighboring video tokens in both spatial and temporal domains. We also add an augmentation-free contrastive learning method to further capture global content.
  arXiv  Detail & Related papers  (2021-06-21T16:48:19Z)
• Relation-aware Hierarchical Attention Framework for Video Question Answering [6.312182279855817]
  We propose a novel Relation-aware Hierarchical Attention (RHA) framework to learn both the static and dynamic relations of the objects in videos. In particular, videos and questions are embedded by pre-trained models firstly to obtain the visual and textual features. We consider the temporal, spatial, and semantic relations, and fuse the multimodal features by hierarchical attention mechanism to predict the answer.
  arXiv  Detail & Related papers  (2021-05-13T09:35:42Z)
• Co-attentional Transformers for Story-Based Video Understanding [24.211255523490692]
  We propose a novel co-attentional transformer model to better capture long-term dependencies seen in visual stories such as dramas. We evaluate our approach on the recently introduced DramaQA dataset which features character-centered video story understanding questions.
  arXiv  Detail & Related papers  (2020-10-27T07:17:09Z)
• 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.