VTD-CLIP: Video-to-Text Discretization via Prompting CLIP

• URL: http://arxiv.org/abs/2503.18407v2
• Date: Tue, 25 Mar 2025 02:24:57 GMT
• Title: VTD-CLIP: Video-to-Text Discretization via Prompting CLIP
• Authors: Wencheng Zhu, Yuexin Wang, Hongxuan Li, Pengfei Zhu, Qinghua Hu,
• Abstract summary: Vision-language models bridge visual and linguistic understanding and have proven to be powerful for video recognition tasks.<n>Existing approaches rely primarily on parameter-efficient fine-tuning of image-text pre-trained models.<n>We propose a video-to-text discretization framework to address limited interpretability and poor generalization due to inadequate temporal modeling.
• Score: 44.51452778561945
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-language models bridge visual and linguistic understanding and have proven to be powerful for video recognition tasks. Existing approaches primarily rely on parameter-efficient fine-tuning of image-text pre-trained models, yet they often suffer from limited interpretability and poor generalization due to inadequate temporal modeling. To address these, we propose a simple yet effective video-to-text discretization framework. Our method repurposes the frozen text encoder to construct a visual codebook from video class labels due to the many-to-one contrastive alignment between visual and textual embeddings in multimodal pretraining. This codebook effectively transforms temporal visual data into textual tokens via feature lookups and offers interpretable video representations through explicit video modeling. Then, to enhance robustness against irrelevant or noisy frames, we introduce a confidence-aware fusion module that dynamically weights keyframes by assessing their semantic relevance via the codebook. Furthermore, our method incorporates learnable text prompts to conduct adaptive codebook updates. Extensive experiments on HMDB-51, UCF-101, SSv2, and Kinetics-400 have validated the superiority of our approach, achieving more competitive improvements over state-of-the-art methods. The code will be publicly available at https://github.com/isxinxin/VTD-CLIP.

Related papers

• Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization [52.63845811751936]
  Video pre-training is challenging due to the modeling of its dynamics video. In this paper, we address such limitations in video pre-training with an efficient video decomposition. Our framework is both capable of comprehending and generating image and video content, as demonstrated by its performance across 13 multimodal benchmarks.
  arXiv  Detail & Related papers  (2024-02-05T16:30:49Z)
• Vamos: Versatile Action Models for Video Understanding [23.631145570126268]
  We propose versatile action models (Vamos), a learning framework powered by a large language model as the reasoner'' We evaluate Vamos on five benchmarks, Ego4D, NeXT-QA, IntentQA, Spacewalk-18, and Ego on its capability to model temporal dynamics, encode visual history, and perform reasoning.
  arXiv  Detail & Related papers  (2023-11-22T17:44:24Z)
• Video-Teller: Enhancing Cross-Modal Generation with Fusion and Decoupling [79.49128866877922]
  Video-Teller is a video-language foundation model that leverages multi-modal fusion and fine-grained modality alignment. Video-Teller boosts the training efficiency by utilizing frozen pretrained vision and language modules. It capitalizes on the robust linguistic capabilities of large language models, enabling the generation of both concise and elaborate video descriptions.
  arXiv  Detail & Related papers  (2023-10-08T03:35:27Z)
• Prompt Switch: Efficient CLIP Adaptation for Text-Video Retrieval [24.691270610091554]
  In this paper, we aim to learn semantically-enhanced representations purely from the video, so that the video representations can be computed offline and reused for different texts. We obtain state-of-the-art performances on three benchmark datasets, i.e., MSR-VTT, MSVD, and LSMDC.
  arXiv  Detail & Related papers  (2023-08-15T08:54:25Z)
• Learning CLIP Guided Visual-Text Fusion Transformer for Video-based Pedestrian Attribute Recognition [23.748227536306295]
  We propose to understand human attributes using video frames that can make full use of temporal information. We formulate the video-based PAR as a vision-language fusion problem and adopt pre-trained big models CLIP to extract the feature embeddings of given video frames.
  arXiv  Detail & Related papers  (2023-04-20T05:18:28Z)
• Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models [149.1331903899298]
  We propose a novel framework called BIKE, which utilizes the cross-modal bridge to explore bidirectional knowledge. We present a Temporal Concept Spotting mechanism that uses the Text-to-Video expertise to capture temporal saliency in a parameter-free manner. Our best model achieves a state-of-the-art accuracy of 88.6% on the challenging Kinetics-400 using the released CLIP model.
  arXiv  Detail & Related papers  (2022-12-31T11:36:53Z)
• Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models [67.31684040281465]
  We present textbfMOV, a simple yet effective method for textbfMultimodal textbfOpen-textbfVocabulary video classification. In MOV, we directly use the vision encoder from pre-trained VLMs with minimal modifications to encode video, optical flow and audio spectrogram.
  arXiv  Detail & Related papers  (2022-07-15T17:59:11Z)
• 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)
• Learning Spatiotemporal Features via Video and Text Pair Discrimination [30.64670449131973]
  Cross-modal pair (CPD) framework captures correlation between video and its associated text. We train our CPD models on both standard video dataset (Kinetics-210k) and uncurated web video dataset (-300k) to demonstrate its effectiveness.
  arXiv  Detail & Related papers  (2020-01-16T08:28:57Z)

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.