A Survey on Natural Language Video Localization
arXiv:2104.00234
Abstract
Natural language video localization (NLVL), which aims to locate a target moment from a video that semantically corresponds to a text query, is a novel and challenging task. Toward this end, in this paper, we present a comprehensive survey of the NLVL algorithms, where we first propose the pipeline of NLVL, and then categorize them into supervised and weakly-supervised methods, following by the analysis of the strengths and weaknesses of each kind of methods. Subsequently, we present the dataset, evaluation protocols and the general performance analysis. Finally, the possible perspectives are obtained by summarizing the existing methods.
References in corpus (20)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- Cross-Modal Interaction Networks for Query-Based Moment Retrieval in Videos
- LXMERT: Learning Cross-Modality Encoder Representations from Transformers
- Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding
- Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs
- TALL: Temporal Activity Localization via Language Query
- VLANet: Video-Language Alignment Network for Weakly-Supervised Video Moment Retrieval
- ExCL: Extractive Clip Localization Using Natural Language Descriptions
- Weakly Supervised Dense Event Captioning in Videos
- Cascaded Boundary Regression for Temporal Action Detection
- Attention on Attention for Image Captioning
- Local-Global Video-Text Interactions for Temporal Grounding
- Span-based Localizing Network for Natural Language Video Localization
- Dense Regression Network for Video Grounding
- Learning Modality Interaction for Temporal Sentence Localization and Event Captioning in Videos
- Reinforcement Learning for Weakly Supervised Temporal Grounding of Natural Language in Untrimmed Videos
- Exploiting Temporal Relationships in Video Moment Localization with Natural Language
- WSLLN: Weakly Supervised Natural Language Localization Networks
- Tree-Structured Policy based Progressive Reinforcement Learning for Temporally Language Grounding in Video