{"total":92,"rows":[{"id":"2206.01670","title":"Egocentric Video-Language Pretraining","created":"2022-06-03","cited_by_count":232,"area":null},{"id":"2108.07781","title":"End-to-End Dense Video Captioning with Parallel Decoding","created":"2021-08-17","cited_by_count":133,"area":null},{"id":"2402.13250","title":"Video ReCap: Recursive Captioning of Hour-Long Videos","created":"2024-02-20","cited_by_count":89,"area":null},{"id":"2110.06615","title":"CLIP4Caption: CLIP for Video Caption","created":"2021-10-13","cited_by_count":88,"area":null},{"id":"2212.05051","title":"VindLU: A Recipe for Effective Video-and-Language Pretraining","created":"2022-12-09","cited_by_count":87,"area":null},{"id":"2206.08522","title":"VLMbench: A Compositional Benchmark for Vision-and-Language Manipulation","created":"2022-06-17","cited_by_count":68,"area":null},{"id":"2208.00847","title":"MAFW: A Large-scale, Multi-modal, Compound Affective Database for Dynamic Facial Expression Recognition in the Wild","created":"2022-08-01","cited_by_count":65,"area":null},{"id":"2309.13925","title":"Towards Surveillance Video-and-Language Understanding: New Dataset, Baselines, and Challenges","created":"2023-09-25","cited_by_count":42,"area":null},{"id":"2309.13952","title":"VidChapters-7M: Video Chapters at Scale","created":"2023-09-25","cited_by_count":39,"area":null},{"id":"2410.00263","title":"Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation","created":"2024-09-30","cited_by_count":39,"area":null},{"id":"2404.07610","title":"Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval","created":"2024-04-11","cited_by_count":36,"area":null},{"id":"2111.12476","title":"Hierarchical Modular Network for Video Captioning","created":"2021-11-24","cited_by_count":32,"area":null},{"id":"2209.03712","title":"Unsupervised Video Object Segmentation via Prototype Memory Network","created":"2022-09-08","cited_by_count":30,"area":null},{"id":"2202.09195","title":"A Review on Methods and Applications in Multimodal Deep Learning","created":"2022-02-18","cited_by_count":29,"area":null},{"id":"2304.11431","title":"A Review of Deep Learning for Video Captioning","created":"2023-04-22","cited_by_count":28,"area":null},{"id":"2108.02183","title":"Enhancing Self-supervised Video Representation Learning via Multi-level Feature Optimization","created":"2021-08-04","cited_by_count":27,"area":null},{"id":"2105.11087","title":"Recent Advances and Trends in Multimodal Deep Learning: A Review","created":"2021-05-24","cited_by_count":26,"area":null},{"id":"2105.14477","title":"Towards Diverse Paragraph Captioning for Untrimmed Videos","created":"2021-05-30","cited_by_count":22,"area":null},{"id":"2210.02884","title":"Vision+X: A Survey on Multimodal Learning in the Light of Data","created":"2022-10-05","cited_by_count":22,"area":null},{"id":"2303.08314","title":"Guided Slot Attention for Unsupervised Video Object Segmentation","created":"2023-03-15","cited_by_count":19,"area":null},{"id":"2108.02359","title":"O2NA: An Object-Oriented Non-Autoregressive Approach for Controllable Video Captioning","created":"2021-08-05","cited_by_count":18,"area":null},{"id":"2211.15076","title":"Refined Semantic Enhancement towards Frequency Diffusion for Video Captioning","created":"2022-11-28","cited_by_count":18,"area":null},{"id":"2303.15616","title":"Fine-grained Audible Video Description","created":"2023-03-27","cited_by_count":18,"area":null},{"id":"2205.10706","title":"GL-RG: Global-Local Representation Granularity for Video Captioning","created":"2022-05-22","cited_by_count":16,"area":null},{"id":"2211.11446","title":"SMAUG: Sparse Masked Autoencoder for Efficient Video-Language Pre-training","created":"2022-11-21","cited_by_count":15,"area":null},{"id":"2408.03006","title":"Dual-path Collaborative Generation Network for Emotional Video Captioning","created":"2024-08-06","cited_by_count":14,"area":null},{"id":"2208.09843","title":"CODER: Coupled Diversity-Sensitive Momentum Contrastive Learning for Image-Text Retrieval","created":"2022-08-21","cited_by_count":13,"area":null},{"id":"2303.13371","title":"Plug-and-Play Regulators for Image-Text Matching","created":"2023-03-23","cited_by_count":10,"area":null},{"id":"2112.01073","title":"Controllable Video Captioning with an Exemplar Sentence","created":"2021-12-02","cited_by_count":9,"area":null},{"id":"2310.10125","title":"Few-shot Action Recognition with Captioning Foundation Models","created":"2023-10-16","cited_by_count":9,"area":null},{"id":"2206.10129","title":"Automatic Concept Extraction for Concept Bottleneck-based Video Classification","created":"2022-06-21","cited_by_count":8,"area":null},{"id":"2208.04215","title":"Boosting Video-Text Retrieval with Explicit High-Level Semantics","created":"2022-08-08","cited_by_count":8,"area":null},{"id":"2305.00607","title":"Boosting Weakly-Supervised Temporal Action Localization with Text Information","created":"2023-05-01","cited_by_count":8,"area":null},{"id":"2404.12782","title":"Sentiment-oriented Transformer-based Variational Autoencoder Network for Live Video Commenting","created":"2024-04-19","cited_by_count":8,"area":null},{"id":"2108.03662","title":"Discriminative Latent Semantic Graph for Video Captioning","created":"2021-08-08","cited_by_count":7,"area":null},{"id":"2310.00670","title":"A Hierarchical Graph-based Approach for Recognition and Description Generation of Bimanual Actions in Videos","created":"2023-10-01","cited_by_count":7,"area":null},{"id":"2504.08222","title":"F$^3$Set: Towards Analyzing Fast, Frequent, and Fine-grained Events from Videos","created":"2025-04-11","cited_by_count":7,"area":null},{"id":"2104.00234","title":"A Survey on Natural Language Video Localization","created":"2021-04-01","cited_by_count":6,"area":null},{"id":"2305.11503","title":"A Topic-aware Summarization Framework with Different Modal Side Information","created":"2023-05-19","cited_by_count":6,"area":null},{"id":"2311.07285","title":"Multi Sentence Description of Complex Manipulation Action Videos","created":"2023-11-13","cited_by_count":6,"area":null},{"id":"2103.14785","title":"A Comprehensive Review of the Video-to-Text Problem","created":"2021-03-27","cited_by_count":5,"area":null},{"id":"2106.14069","title":"Saying the Unseen: Video Descriptions via Dialog Agents","created":"2021-06-26","cited_by_count":5,"area":null},{"id":"2210.14512","title":"End-to-End Multimodal Representation Learning for Video Dialog","created":"2022-10-26","cited_by_count":5,"area":null},{"id":"2310.02522","title":"SCB-Dataset3: A Benchmark for Detecting Student Classroom Behavior","created":"2023-10-04","cited_by_count":5,"area":null},{"id":"2507.04815","title":"From Vision To Language through Graph of Events in Space and Time: An Explainable Self-supervised Approach","created":"2025-07-07","cited_by_count":5,"area":null},{"id":"2108.06458","title":"Cross-Modal Graph with Meta Concepts for Video Captioning","created":"2021-08-14","cited_by_count":4,"area":null},{"id":"2211.09469","title":"Visual Commonsense-aware Representation Network for Video Captioning","created":"2022-11-17","cited_by_count":4,"area":null},{"id":"2307.02682","title":"Zero-Shot Dense Video Captioning by Jointly Optimizing Text and Moment","created":"2023-07-05","cited_by_count":4,"area":null},{"id":"2309.08612","title":"Explaining Vision and Language through Graphs of Events in Space and Time","created":"2023-08-29","cited_by_count":4,"area":null},{"id":"2509.04602","title":"Sali4Vid: Saliency-Aware Video Reweighting and Adaptive Caption Retrieval for Dense Video Captioning","created":"2025-09-04","cited_by_count":4,"area":null},{"id":"2606.08566","title":"Towards Accurate Emotion-Attributed Video Captioning via Fine-grained Emotion-Cause Pair Extraction","created":"2026-06-07","cited_by_count":4,"area":null},{"id":"2201.00985","title":"Variational Stacked Local Attention Networks for Diverse Video Captioning","created":"2022-01-04","cited_by_count":3,"area":null},{"id":"2204.05976","title":"Video Captioning: a comparative review of where we are and which could be the route","created":"2022-04-12","cited_by_count":3,"area":null},{"id":"2209.12694","title":"Multi-modal Video Chapter Generation","created":"2022-09-26","cited_by_count":3,"area":null},{"id":"2306.12559","title":"Exploring the Role of Audio in Video Captioning","created":"2023-06-21","cited_by_count":3,"area":null},{"id":"2408.01349","title":"PC$^2$: Pseudo-Classification Based Pseudo-Captioning for Noisy Correspondence Learning in Cross-Modal Retrieval","created":"2024-08-02","cited_by_count":3,"area":null},{"id":"2107.11707","title":"Boosting Video Captioning with Dynamic Loss Network","created":"2021-07-25","cited_by_count":2,"area":null},{"id":"2112.01062","title":"Syntax Customized Video Captioning by Imitating Exemplar Sentences","created":"2021-12-02","cited_by_count":2,"area":null},{"id":"2112.14088","title":"Synchronized Audio-Visual Frames with Fractional Positional Encoding for Transformers in Video-to-Text Translation","created":"2021-12-28","cited_by_count":2,"area":null},{"id":"2205.03039","title":"Dual-Level Decoupled Transformer for Video Captioning","created":"2022-05-06","cited_by_count":2,"area":null},{"id":"2401.04903","title":"SnapCap: Efficient Snapshot Compressive Video Captioning","created":"2024-01-10","cited_by_count":2,"area":null},{"id":"2510.10671","title":"Image-to-Video Transfer Learning based on Image-Language Foundation Models: A Comprehensive Survey","created":"2025-10-12","cited_by_count":2,"area":null},{"id":"2606.23436","title":"Rethinking Object-Centric Representations for Video Dynamics Modeling","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2101.00359","title":"Video Captioning in Compressed Video","created":"2021-01-02","cited_by_count":1,"area":null},{"id":"2101.05806","title":"Exploration of Visual Features and their weighted-additive fusion for Video Captioning","created":"2021-01-14","cited_by_count":1,"area":null},{"id":"2102.05067","title":"The Role of the Input in Natural Language Video Description","created":"2021-02-09","cited_by_count":1,"area":null},{"id":"2110.08578","title":"Visual-aware Attention Dual-stream Decoder for Video Captioning","created":"2021-10-16","cited_by_count":1,"area":null},{"id":"2111.07370","title":"Co-segmentation Inspired Attention Module for Video-based Computer Vision Tasks","created":"2021-11-14","cited_by_count":1,"area":null},{"id":"2112.13758","title":"Bridging the Gap: Using Deep Acoustic Representations to Learn Grounded Language from Percepts and Raw Speech","created":"2021-12-27","cited_by_count":1,"area":null},{"id":"2308.06685","title":"Video Captioning with Aggregated Features Based on Dual Graphs and Gated Fusion","created":"2023-08-13","cited_by_count":1,"area":null},{"id":"2312.01575","title":"A Challenging Multimodal Video Summary: Simultaneously Extracting and Generating Keyframe-Caption Pairs from Video","created":"2023-12-04","cited_by_count":1,"area":null},{"id":"2411.01975","title":"SPECTRUM: Semantic Processing and Emotion-informed video-Captioning Through Retrieval and Understanding Modalities","created":"2024-11-04","cited_by_count":1,"area":null},{"id":"2505.12499","title":"Rebalancing Contrastive Alignment with Bottlenecked Semantic Increments in Text-Video Retrieval","created":"2025-05-18","cited_by_count":1,"area":null},{"id":"2506.20583","title":"Dense Video Captioning using Graph-based Sentence Summarization","created":"2025-06-25","cited_by_count":1,"area":null},{"id":"2603.05437","title":"SAIL: Similarity-Aware Guidance and Inter-Caption Augmentation-based Learning for Weakly-Supervised Dense Video Captioning","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2603.11439","title":"Stay in your Lane: Role Specific Queries with Overlap Suppression Loss for Dense Video Captioning","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2603.11460","title":"Follow the Saliency: Supervised Saliency for Retrieval-augmented Dense Video Captioning","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2607.29045","title":"Adaptive Emotional Video Captioning via Affective Heterogeneous Graph Reasoning and Multi-task Joint Learning","created":"2026-07-31","cited_by_count":1,"area":null},{"id":"2201.09153","title":"An Integrated Approach for Video Captioning and Applications","created":"2022-01-23","cited_by_count":0,"area":null},{"id":"2203.06663","title":"Global2Local: A Joint-Hierarchical Attention for Video Captioning","created":"2022-03-13","cited_by_count":0,"area":null},{"id":"2305.12940","title":"GEST: the Graph of Events in Space and Time as a Common Representation between Vision and Language","created":"2023-05-22","cited_by_count":0,"area":null},{"id":"2306.13420","title":"Towards Unseen Triples: Effective Text-Image-joint Learning for Scene Graph Generation","created":"2023-06-23","cited_by_count":0,"area":null},{"id":"2310.16267","title":"Student Classroom Behavior Detection based on Spatio-Temporal Network and Multi-Model Fusion","created":"2023-10-25","cited_by_count":0,"area":null},{"id":"2407.12005","title":"VCEval: Rethinking What is a Good Educational Video and How to Automatically Evaluate It","created":"2024-06-15","cited_by_count":0,"area":null},{"id":"2410.16624","title":"EVC-MF: End-to-end Video Captioning Network with Multi-scale Features","created":"2024-10-22","cited_by_count":0,"area":null},{"id":"2411.06872","title":"Multi-Modal interpretable automatic video captioning","created":"2024-11-11","cited_by_count":0,"area":null},{"id":"2504.15921","title":"ViSMaP: Unsupervised Hour-long Video Summarisation by Meta-Prompting","created":"2025-04-22","cited_by_count":0,"area":null},{"id":"2506.16082","title":"PR-DETR: Injecting Position and Relation Prior for Dense Video Captioning","created":"2025-06-19","cited_by_count":0,"area":null},{"id":"2506.20567","title":"Show, Tell and Summarize: Dense Video Captioning Using Visual Cue Aided Sentence Summarization","created":"2025-06-25","cited_by_count":0,"area":null},{"id":"2603.08658","title":"Context-free Self-Conditioned GAN for Trajectory Forecasting","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2609.04183","title":"Seeing Before Synthesizing: VLM-Guided Transition Event Discovery for Weakly-Supervised Dense Video Captioning","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.36776","title":"Causal-EVC: Breaking Emotional Spurious Causality via Spatiotemporal Grounding and Counterfactual Intervention","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}