Video-Text Representation Learning via Differentiable Weak Temporal Alignment

• URL: http://arxiv.org/abs/2203.16784v1
• Date: Thu, 31 Mar 2022 04:13:16 GMT
• Title: Video-Text Representation Learning via Differentiable Weak Temporal Alignment
• Authors: Dohwan Ko, Joonmyung Choi, Juyeon Ko, Shinyeong Noh, Kyoung-Woon On, Eun-Sol Kim, Hyunwoo J. Kim
• Abstract summary: Learning generic joint representations for video and text by a supervised method requires a substantial amount of manually annotated video datasets. It is still challenging to learn joint embeddings of video and text in a self-supervised manner, due to its ambiguity and non-sequential alignment. We propose Video-Text Temporally Weak Alignment-based Contrastive Learning (VT-TWINS) to capture significant information from noisy and weakly correlated data.
• Score: 11.967313324773668
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learning generic joint representations for video and text by a supervised method requires a prohibitively substantial amount of manually annotated video datasets. As a practical alternative, a large-scale but uncurated and narrated video dataset, HowTo100M, has recently been introduced. But it is still challenging to learn joint embeddings of video and text in a self-supervised manner, due to its ambiguity and non-sequential alignment. In this paper, we propose a novel multi-modal self-supervised framework Video-Text Temporally Weak Alignment-based Contrastive Learning (VT-TWINS) to capture significant information from noisy and weakly correlated data using a variant of Dynamic Time Warping (DTW). We observe that the standard DTW inherently cannot handle weakly correlated data and only considers the globally optimal alignment path. To address these problems, we develop a differentiable DTW which also reflects local information with weak temporal alignment. Moreover, our proposed model applies a contrastive learning scheme to learn feature representations on weakly correlated data. Our extensive experiments demonstrate that VT-TWINS attains significant improvements in multi-modal representation learning and outperforms various challenging downstream tasks. Code is available at https://github.com/mlvlab/VT-TWINS.

Related papers

• Dual Learning with Dynamic Knowledge Distillation and Soft Alignment for Partially Relevant Video Retrieval [53.54695034420311]
  In practice, videos are typically untrimmed in long durations with much more complicated background content.<n>We propose a novel framework that distills generalization knowledge from a powerful large-scale vision-language pre-trained model.<n>Experiment results demonstrate that our proposed model achieves state-of-the-art performance on TVR, ActivityNet, and Charades-STA datasets.
  arXiv  Detail & Related papers  (2025-10-14T08:38:20Z)
• VideoLights: Feature Refinement and Cross-Task Alignment Transformer for Joint Video Highlight Detection and Moment Retrieval [8.908777234657046]
  Large-language and vision-language models (LLM/LVLMs) have gained prominence across various domains. Here we propose VideoLights, a novel HD/MR framework addressing these limitations through (i) Convolutional Projection and Feature Refinement modules. Comprehensive experiments on QVHighlights, TVSum, and Charades-STA benchmarks demonstrate state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-12-02T14:45:53Z)
• Dual-Modal Attention-Enhanced Text-Video Retrieval with Triplet Partial Margin Contrastive Learning [35.404100473539195]
  Text-video retrieval aims to rank relevant text/video higher than irrelevant ones. Recent contrastive learning methods have shown promising results for text-video retrieval. This paper improves contrastive learning using two novel techniques.
  arXiv  Detail & Related papers  (2023-09-20T06:08:11Z)
• Zero-Shot Video Moment Retrieval from Frozen Vision-Language Models [58.17315970207874]
  We propose a zero-shot method for adapting generalisable visual-textual priors from arbitrary VLM to facilitate moment-text alignment. Experiments conducted on three VMR benchmark datasets demonstrate the notable performance advantages of our zero-shot algorithm.
  arXiv  Detail & Related papers  (2023-09-01T13:06:50Z)
• Learning from Semantic Alignment between Unpaired Multiviews for Egocentric Video Recognition [23.031934558964473]
  We propose Semantics-based Unpaired Multiview Learning (SUM-L) to tackle this unpaired multiview learning problem. Key idea is to build cross-view pseudo-pairs and do view-invariant alignment by leveraging the semantic information of videos. Our method also outperforms multiple existing view-alignment methods, under the more challenging scenario.
  arXiv  Detail & Related papers  (2023-08-22T15:10:42Z)
• Transform-Equivariant Consistency Learning for Temporal Sentence Grounding [66.10949751429781]
  We introduce a novel Equivariant Consistency Regulation Learning framework to learn more discriminative representations for each video. Our motivation comes from that the temporal boundary of the query-guided activity should be consistently predicted. In particular, we devise a self-supervised consistency loss module to enhance the completeness and smoothness of the augmented video.
  arXiv  Detail & Related papers  (2023-05-06T19:29:28Z)
• 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)
• Weakly-supervised Representation Learning for Video Alignment and Analysis [16.80278496414627]
  This paper introduces LRProp -- a novel weakly-supervised representation learning approach. The proposed algorithm uses also a regularized SoftDTW loss for better tuning the learned features. Our novel representation learning paradigm consistently outperforms the state of the art on temporal alignment tasks.
  arXiv  Detail & Related papers  (2023-02-08T14:01:01Z)
• Mitigating Representation Bias in Action Recognition: Algorithms and Benchmarks [76.35271072704384]
  Deep learning models perform poorly when applied to videos with rare scenes or objects. We tackle this problem from two different angles: algorithm and dataset. We show that the debiased representation can generalize better when transferred to other datasets and tasks.
  arXiv  Detail & Related papers  (2022-09-20T00:30:35Z)
• ASCNet: Self-supervised Video Representation Learning with Appearance-Speed Consistency [62.38914747727636]
  We study self-supervised video representation learning, which is a challenging task due to 1) a lack of labels for explicit supervision and 2) unstructured and noisy visual information. Existing methods mainly use contrastive loss with video clips as the instances and learn visual representation by discriminating instances from each other. In this paper, we observe that the consistency between positive samples is the key to learn robust video representations.
  arXiv  Detail & Related papers  (2021-06-04T08:44:50Z)
• Video Understanding as Machine Translation [53.59298393079866]
  We tackle a wide variety of downstream video understanding tasks by means of a single unified framework. We report performance gains over the state-of-the-art on several downstream tasks including video classification (EPIC-Kitchens), question answering (TVQA), captioning (TVC, YouCook2, and MSR-VTT)
  arXiv  Detail & Related papers  (2020-06-12T14:07:04Z)

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.