Align before Adapt: Leveraging Entity-to-Region Alignments for Generalizable Video Action Recognition

• URL: http://arxiv.org/abs/2311.15619v3
• Date: Wed, 20 Mar 2024 18:27:25 GMT
• Title: Align before Adapt: Leveraging Entity-to-Region Alignments for Generalizable Video Action Recognition
• Authors: Yifei Chen, Dapeng Chen, Ruijin Liu, Sai Zhou, Wenyuan Xue, Wei Peng,
• Abstract summary: We propose a novel "Align before Adapt" (ALT) paradigm for video representation learning. We exploit the entity-to-region alignments for each frame. The alignments are fulfilled by matching the region-aware image embeddings to an offline-constructed text corpus. ALT demonstrates competitive performance while maintaining remarkably low computational costs.
• Score: 16.828560953073495
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large-scale visual-language pre-trained models have achieved significant success in various video tasks. However, most existing methods follow an "adapt then align" paradigm, which adapts pre-trained image encoders to model video-level representations and utilizes one-hot or text embedding of the action labels for supervision. This paradigm overlooks the challenge of mapping from static images to complicated activity concepts. In this paper, we propose a novel "Align before Adapt" (ALT) paradigm. Prior to adapting to video representation learning, we exploit the entity-to-region alignments for each frame. The alignments are fulfilled by matching the region-aware image embeddings to an offline-constructed text corpus. With the aligned entities, we feed their text embeddings to a transformer-based video adapter as the queries, which can help extract the semantics of the most important entities from a video to a vector. This paradigm reuses the visual-language alignment of VLP during adaptation and tries to explain an action by the underlying entities. This helps understand actions by bridging the gap with complex activity semantics, particularly when facing unfamiliar or unseen categories. ALT demonstrates competitive performance while maintaining remarkably low computational costs. In fully supervised experiments, it achieves 88.1% top-1 accuracy on Kinetics-400 with only 4947 GFLOPs. Moreover, ALT outperforms the previous state-of-the-art methods in both zero-shot and few-shot experiments, emphasizing its superior generalizability across various learning scenarios.

Related papers

• Open-Vocabulary Spatio-Temporal Action Detection [59.91046192096296]
  Open-vocabulary-temporal action detection (OV-STAD) is an important fine-grained video understanding task. OV-STAD requires training a model on a limited set of base classes with box and label supervision. To better adapt the holistic VLM for the fine-grained action detection task, we carefully fine-tune it on the localized video region-text pairs.
  arXiv  Detail & Related papers  (2024-05-17T14:52:47Z)
• VaQuitA: Enhancing Alignment in LLM-Assisted Video Understanding [63.075626670943116]
  We introduce a cutting-edge framework, VaQuitA, designed to refine the synergy between video and textual information. At the data level, instead of sampling frames uniformly, we implement a sampling method guided by CLIP-score rankings. At the feature level, we integrate a trainable Video Perceiver alongside a Visual-Query Transformer.
  arXiv  Detail & Related papers  (2023-12-04T19:48:02Z)
• Contrastive Vision-Language Alignment Makes Efficient Instruction Learner [31.281236193979165]
  We study the task of extending the large language model (LLM) into a vision-language instruction-following model. Existing methods typically train a visual adapter to align the representation between a pre-trained vision transformer (ViT) and the LLM by a generative image captioning loss. We propose CG-VLM that applies Contrastive and Generative alignment objectives to effectively align the representation of ViT and LLM.
  arXiv  Detail & Related papers  (2023-11-29T03:29:46Z)
• Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer [79.20605034378187]
  Video-language pre-trained models have shown remarkable success in guiding video question-answering tasks. Due to the length of video sequences, training large-scale video-based models incurs considerably higher costs than training image-based ones. This motivates us to leverage the knowledge from image-based pretraining, despite the obvious gaps between image and video domains.
  arXiv  Detail & Related papers  (2023-08-16T15:00:50Z)
• Towards Generalisable Video Moment Retrieval: Visual-Dynamic Injection to Image-Text Pre-Training [70.83385449872495]
  The correlation between the vision and text is essential for video moment retrieval (VMR) Existing methods rely on separate pre-training feature extractors for visual and textual understanding. We propose a generic method, referred to as Visual-Dynamic Injection (VDI), to empower the model's understanding of video moments.
  arXiv  Detail & Related papers  (2023-02-28T19:29:05Z)
• Part-level Action Parsing via a Pose-guided Coarse-to-Fine Framework [108.70949305791201]
  Part-level Action Parsing (PAP) aims to not only predict the video-level action but also recognize the frame-level fine-grained actions or interactions of body parts for each person in the video. In particular, our framework first predicts the video-level class of the input video, then localizes the body parts and predicts the part-level action. Our framework achieves state-of-the-art performance and outperforms existing methods over a 31.10% ROC score.
  arXiv  Detail & Related papers  (2022-03-09T01:30:57Z)
• Align and Prompt: Video-and-Language Pre-training with Entity Prompts [111.23364631136339]
  Video-and-language pre-training has shown promising improvements on various downstream tasks. We propose Align and Prompt: an efficient and effective video-and-language pre-training framework with better cross-modal alignment. Our code and pre-trained models will be released.
  arXiv  Detail & Related papers  (2021-12-17T15:55:53Z)
• Prompting Visual-Language Models for Efficient Video Understanding [28.754997650215486]
  This paper presents a simple method to efficiently adapt one pre-trained visual-language model to novel tasks with minimal training. To bridge the gap between static images and videos, temporal information is encoded with lightweight Transformers stacking on top of frame-wise visual features.
  arXiv  Detail & Related papers  (2021-12-08T18:58:16Z)
• ActionCLIP: A New Paradigm for Video Action Recognition [14.961103794667341]
  We provide a new perspective on action recognition by attaching importance to the semantic information of label texts. We propose a new paradigm based on this multimodal learning framework for action recognition, which we dub "pre-train, prompt and fine-tune"
  arXiv  Detail & Related papers  (2021-09-17T11:21:34Z)

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.