{"total":87,"rows":[{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177,"area":null},{"id":"2104.08860","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","created":"2021-04-18","cited_by_count":651,"area":null},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602,"area":null},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537,"area":null},{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485,"area":null},{"id":"2102.06183","title":"Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling","created":"2021-02-11","cited_by_count":484,"area":null},{"id":"2207.07285","title":"X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval","created":"2022-07-15","cited_by_count":280,"area":null},{"id":"2111.10337","title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","created":"2021-11-19","cited_by_count":226,"area":null},{"id":"2111.13196","title":"SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning","created":"2021-11-25","cited_by_count":162,"area":null},{"id":"2112.09583","title":"Align and Prompt: Video-and-Language Pre-training with Entity Prompts","created":"2021-12-17","cited_by_count":149,"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":"2104.08271","title":"TEACHTEXT: CrossModal Generalized Distillation for Text-Video Retrieval","created":"2021-04-16","cited_by_count":81,"area":null},{"id":"2206.07160","title":"LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling","created":"2022-06-14","cited_by_count":73,"area":null},{"id":"2106.06965","title":"Contrastive Attention for Automatic Chest X-ray Report Generation","created":"2021-06-13","cited_by_count":71,"area":null},{"id":"2112.00656","title":"Object-aware Video-language Pre-training for Retrieval","created":"2021-12-01","cited_by_count":57,"area":null},{"id":"2303.14369","title":"Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning","created":"2023-03-25","cited_by_count":45,"area":null},{"id":"2207.10362","title":"LocVTP: Video-Text Pre-training for Temporal Localization","created":"2022-07-21","cited_by_count":44,"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":"2107.13782","title":"Multimodal Co-learning: Challenges, Applications with Datasets, Recent Advances and Future Directions","created":"2021-07-29","cited_by_count":35,"area":null},{"id":"2111.12476","title":"Hierarchical Modular Network for Video Captioning","created":"2021-11-24","cited_by_count":32,"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":"2303.15932","title":"Unify, Align and Refine: Multi-Level Semantic Alignment for Radiology Report Generation","created":"2023-03-28","cited_by_count":23,"area":null},{"id":"2112.01194","title":"Video-Text Pre-training with Learned Regions","created":"2021-12-02","cited_by_count":20,"area":null},{"id":"2209.13307","title":"Text-Adaptive Multiple Visual Prototype Matching for Video-Text Retrieval","created":"2022-09-27","cited_by_count":20,"area":null},{"id":"2310.11612","title":"Balance Act: Mitigating Hubness in Cross-Modal Retrieval with Query and Gallery Banks","created":"2023-10-17","cited_by_count":20,"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":"2301.12644","title":"Tagging before Alignment: Integrating Multi-Modal Tags for Video-Text Retrieval","created":"2023-01-30","cited_by_count":18,"area":null},{"id":"2212.13738","title":"TempCLR: Temporal Alignment Representation with Contrastive Learning","created":"2022-12-28","cited_by_count":15,"area":null},{"id":"2103.04037","title":"Perspectives and Prospects on Transformer Architecture for Cross-Modal Tasks with Language and Vision","created":"2021-03-06","cited_by_count":14,"area":null},{"id":"2211.12148","title":"Aligning Source Visual and Target Language Domains for Unpaired Video Captioning","created":"2022-11-22","cited_by_count":14,"area":null},{"id":"2107.11851","title":"Transcript to Video: Efficient Clip Sequencing from Texts","created":"2021-07-25","cited_by_count":13,"area":null},{"id":"2208.04897","title":"Sports Video Analysis on Large-Scale Data","created":"2022-08-09","cited_by_count":13,"area":null},{"id":"2408.08074","title":"A Survey on Integrated Sensing, Communication, and Computation","created":"2024-08-15","cited_by_count":12,"area":null},{"id":"2111.15162","title":"CLIP Meets Video Captioning: Concept-Aware Representation Learning Does Matter","created":"2021-11-30","cited_by_count":11,"area":null},{"id":"2209.11388","title":"LGDN: Language-Guided Denoising Network for Video-Language Modeling","created":"2022-09-23","cited_by_count":11,"area":null},{"id":"2310.03635","title":"CLEVRER-Humans: Describing Physical and Causal Events the Human Way","created":"2023-10-05","cited_by_count":11,"area":null},{"id":"2108.08217","title":"X-modaler: A Versatile and High-performance Codebase for Cross-modal Analytics","created":"2021-08-18","cited_by_count":10,"area":null},{"id":"2110.11298","title":"Video and Text Matching with Conditioned Embeddings","created":"2021-10-21","cited_by_count":10,"area":null},{"id":"2109.02955","title":"Sensor-Augmented Egocentric-Video Captioning with Dynamic Modal Attention","created":"2021-09-07","cited_by_count":9,"area":null},{"id":"2112.01073","title":"Controllable Video Captioning with an Exemplar Sentence","created":"2021-12-02","cited_by_count":9,"area":null},{"id":"2404.08229","title":"Enhancing Traffic Safety with Parallel Dense Video Captioning for End-to-End Event Analysis","created":"2024-04-12","cited_by_count":9,"area":null},{"id":"2405.11483","title":"MICap: A Unified Model for Identity-aware Movie Descriptions","created":"2024-05-19","cited_by_count":9,"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":"2103.11313","title":"PGT: A Progressive Method for Training Models on Long Videos","created":"2021-03-21","cited_by_count":7,"area":null},{"id":"2412.14585","title":"HiCM$^2$: Hierarchical Compact Memory Modeling for Dense Video Captioning","created":"2024-12-19","cited_by_count":7,"area":null},{"id":"2210.05039","title":"Contrastive Video-Language Learning with Fine-grained Frame Sampling","created":"2022-10-10","cited_by_count":6,"area":null},{"id":"2303.03638","title":"Collaboration with Conversational AI Assistants for UX Evaluation: Questions and How to Ask them (Voice vs. Text)","created":"2023-03-07","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":"2112.08455","title":"Dense Video Captioning Using Unsupervised Semantic Information","created":"2021-12-15","cited_by_count":5,"area":null},{"id":"2404.00973","title":"VideoDistill: Language-aware Vision Distillation for Video Question Answering","created":"2024-04-01","cited_by_count":5,"area":null},{"id":"2202.05728","title":"Deep soccer captioning with transformer: dataset, semantics-related losses, and multi-level evaluation","created":"2022-02-11","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":"2303.06458","title":"ZeroNLG: Aligning and Autoencoding Domains for Zero-Shot Multimodal and Multilingual Natural Language Generation","created":"2023-03-11","cited_by_count":4,"area":null},{"id":"2309.15857","title":"A Survey on Image-text Multimodal Models","created":"2023-09-23","cited_by_count":4,"area":null},{"id":"2108.02147","title":"Optimizing Latency for Online Video CaptioningUsing Audio-Visual Transformers","created":"2021-08-04","cited_by_count":3,"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":"2203.06356","title":"Taking an Emotional Look at Video Paragraph Captioning","created":"2022-03-12","cited_by_count":3,"area":null},{"id":"2305.01928","title":"Visual Transformation Telling","created":"2023-05-03","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":"2203.07720","title":"Revitalize Region Feature for Democratizing Video-Language Pre-training of Retrieval","created":"2022-03-15","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":"2208.09266","title":"Diverse Video Captioning by Adaptive Spatio-temporal Attention","created":"2022-08-19","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":"2102.05067","title":"The Role of the Input in Natural Language Video Description","created":"2021-02-09","cited_by_count":1,"area":null},{"id":"2109.04600","title":"EVOQUER: Enhancing Temporal Grounding with Video-Pivoted BackQuery Generation","created":"2021-09-10","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":"2202.10828","title":"Exploiting long-term temporal dynamics for video captioning","created":"2022-02-22","cited_by_count":1,"area":null},{"id":"2203.05408","title":"Attacks as Defenses: Designing Robust Audio CAPTCHAs Using Attacks on Automatic Speech Recognition Systems","created":"2022-03-10","cited_by_count":1,"area":null},{"id":"2212.10690","title":"METEOR Guided Divergence for Video Captioning","created":"2022-12-20","cited_by_count":1,"area":null},{"id":"2212.11109","title":"MAViC: Multimodal Active Learning for Video Captioning","created":"2022-12-11","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":"2311.04480","title":"CLearViD: Curriculum Learning for Video Description","created":"2023-11-08","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":"2203.06663","title":"Global2Local: A Joint-Hierarchical Attention for Video Captioning","created":"2022-03-13","cited_by_count":0,"area":null},{"id":"2208.11061","title":"Large-Scale Traffic Congestion Prediction based on Multimodal Fusion and Representation Mapping","created":"2022-08-23","cited_by_count":0,"area":null},{"id":"2302.02224","title":"TAP: The Attention Patch for Cross-Modal Knowledge Transfer from Unlabeled Modality","created":"2023-02-04","cited_by_count":0,"area":null},{"id":"2309.09611","title":"Collaborative Three-Stream Transformers for Video Captioning","created":"2023-09-18","cited_by_count":0,"area":null},{"id":"2312.07418","title":"Attention Based Encoder Decoder Model for Video Captioning in Nepali (2023)","created":"2023-12-12","cited_by_count":0,"area":null},{"id":"2312.12721","title":"Cross-Modal Reasoning with Event Correlation for Video Question Answering","created":"2023-12-20","cited_by_count":0,"area":null},{"id":"2406.01604","title":"An Empirical Study of Excitation and Aggregation Design Adaptions in CLIP4Clip for Video-Text Retrieval","created":"2024-05-25","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":"2411.06872","title":"Multi-Modal interpretable automatic video captioning","created":"2024-11-11","cited_by_count":0,"area":null},{"id":"2502.13754","title":"Capturing Rich Behavior Representations: A Dynamic Action Semantic-Aware Graph Transformer for Video Captioning","created":"2025-02-19","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}],"next_cursor":null}