paper-with-me

Papers

Collaborative Temporal Consistency Learning for Point-supervised Natural Language Video Localization

2025-03-22 · Zhuo Tao, Liang Li, Qi Chen, Yunbin Tu, Zheng-Jun Zha, Ming-Hsuan Yang, Yuankai Qi, Qingming Huang

Natural language video localization (NLVL) is a crucial task in video understanding that aims to localize the target moment in videos specified by a given language description. Recently, a point-supervised paradigm has been presented to address this task, requiring only a single annotated frame within the target moment rather than complete temporal boundaries. Compared with the fully-supervised paradigm, it offers a balance between localization accuracy and annotation cost. However, due to the absence of complete annotation, it is challenging to align the video content with language descriptions, consequently hindering accurate moment prediction. To address this problem, we propose a new COllaborative Temporal consistEncy Learning (COTEL) framework that leverages the synergy between saliency detection and moment localization to strengthen the video-language alignment. Specifically, we first design a frame- and a segment-level Temporal Consistency Learning (TCL) module that models semantic alignment across frame saliencies and sentence-moment pairs. Then, we design a cross-consistency guidance scheme, including a Frame-level Consistency Guidance (FCG) and a Segment-level Consistency Guidance (SCG), that enables the two temporal consistency learning paths to reinforce each other mutually. Further, we introduce a Hierarchical Contrastive Alignment Loss (HCAL) to comprehensively align the video and text query. Extensive experiments on two benchmarks demonstrate that our method performs favorably against SoTA approaches. We will release all the source codes.

📄 PDF Abstract BibTeX arXiv:2503.17651

Code (0)

등록된 구현이 없습니다.

Tasks

Saliency DetectionSentenceVideo Understanding

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Self-Ensemling for 3D Point Cloud Domain Adaption

2021-12-10 · Qing Li, Xiaojiang Peng, Chuan Yan, Pan Gao 외

Recently 3D point cloud learning has been a hot topic in computer vision and autonomous driving. Due to the fact that it is difficult to manually annotate a qualitative large-scale 3D point cloud dataset, unsupervised do…

Autonomous DrivingDomain AdaptationSelf-Supervised LearningUnsupervised Domain Adaptation

Exploring the Temporal Consistency for Point-Level Weakly-Supervised Temporal Action Localization

2026-02-05 · Yunchuan Ma, Laiyun Qing, Guorong Li, Yuqing Liu 외 arxiv

Point-supervised Temporal Action Localization (PTAL) adopts a lightly frame-annotated paradigm (\textit{i.e.}, labeling only a single frame per action instance) to train a model to effectively locate action instances wit…

Weakly-supervised Temporal Action LocalizationMulti-Task Learning

Learning Natural Consistency Representation for Face Forgery Video Detection

2024-07-15 · Daichi Zhang, Zihao Xiao, Shikun Li, Fanzhao Lin 외

Face Forgery videos have elicited critical social public concerns and various detectors have been proposed. However, fully-supervised detectors may lead to easily overfitting to specific forgery methods or videos, and ex…

Representation LearningVideo Classification

PredNext: Explicit Cross-View Temporal Prediction for Unsupervised Learning in Spiking Neural Networks

2025-09-29 · Yiting Dong, Jianhao Ding, Zijie Xu, Tong Bu 외 arxiv

Spiking Neural Networks (SNNs), with their temporal processing capabilities and biologically plausible dynamics, offer a natural platform for unsupervised representation learning. However, current unsupervised SNNs predo…

Self-Supervised LearningRepresentation Learning

Collaborative Learning for Weakly Supervised Object Detection

2018-02-10 · Jiajie Wang, Jiangchao Yao, Ya zhang, Rui Zhang

Weakly supervised object detection has recently received much attention, since it only requires image-level labels instead of the bounding-box labels consumed in strongly supervised learning. Nevertheless, the save in la…

Objectobject-detectionObject DetectionWeakly Supervised Object Detection