{"total":80,"rows":[{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744,"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":"2108.07781","title":"End-to-End Dense Video Captioning with Parallel Decoding","created":"2021-08-17","cited_by_count":133,"area":null},{"id":"2203.15086","title":"X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval","created":"2022-03-28","cited_by_count":128,"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":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"area":null},{"id":"2103.10095","title":"On Semantic Similarity in Video Retrieval","created":"2021-03-18","cited_by_count":46,"area":null},{"id":"2303.12060","title":"VideoXum: Cross-modal Visual and Textural Summarization of Videos","created":"2023-03-21","cited_by_count":41,"area":null},{"id":"2406.05615","title":"Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives","created":"2024-06-09","cited_by_count":37,"area":null},{"id":"2102.00831","title":"Semantic Grouping Network for Video Captioning","created":"2021-02-01","cited_by_count":34,"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":"2105.14477","title":"Towards Diverse Paragraph Captioning for Untrimmed Videos","created":"2021-05-30","cited_by_count":22,"area":null},{"id":"2210.02081","title":"Locate before Answering: Answer Guided Question Localization for Video Question Answering","created":"2022-10-05","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":"2112.03572","title":"Question Answering Survey: Directions, Challenges, Datasets, Evaluation Matrices","created":"2021-12-07","cited_by_count":17,"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":"2208.04897","title":"Sports Video Analysis on Large-Scale Data","created":"2022-08-09","cited_by_count":13,"area":null},{"id":"2104.14236","title":"Learning Multi-Attention Context Graph for Group-Based Re-Identification","created":"2021-04-29","cited_by_count":12,"area":null},{"id":"2112.00967","title":"Relational Graph Learning for Grounded Video Description Generation","created":"2021-12-02","cited_by_count":12,"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":"2106.03158","title":"Transferring Knowledge from Text to Video: Zero-Shot Anticipation for Procedural Actions","created":"2021-06-06","cited_by_count":10,"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":"2107.03050","title":"Controlled Caption Generation for Images Through Adversarial Attacks","created":"2021-07-07","cited_by_count":9,"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":"2107.08323","title":"Agent-Environment Network for Temporal Action Proposal Generation","created":"2021-07-17","cited_by_count":8,"area":null},{"id":"2203.01933","title":"Temporal Context Matters: Enhancing Single Image Prediction with Disease Progression Representations","created":"2022-03-02","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":"2108.04229","title":"Looking for the Signs: Identifying Isolated Sign Instances in Continuous Video Footage","created":"2021-07-21","cited_by_count":7,"area":null},{"id":"2101.01447","title":"End-to-End Video Question-Answer Generation with Generator-Pretester Network","created":"2021-01-05","cited_by_count":6,"area":null},{"id":"2203.08942","title":"ABN: Agent-Aware Boundary Networks for Temporal Action Proposal Generation","created":"2022-03-16","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":"2108.06458","title":"Cross-Modal Graph with Meta Concepts for Video Captioning","created":"2021-08-14","cited_by_count":4,"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":"2209.15501","title":"A Closer Look at Temporal Ordering in the Segmentation of Instructional Videos","created":"2022-09-30","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":"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":"2304.06020","title":"VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEs","created":"2023-04-12","cited_by_count":3,"area":null},{"id":"2406.02748","title":"Story Generation from Visual Inputs: Techniques, Related Tasks, and Challenges","created":"2024-06-04","cited_by_count":3,"area":null},{"id":"2508.21809","title":"VoCap: Video Object Captioning and Segmentation from Any Prompt","created":"2025-08-29","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":"2111.10146","title":"DVCFlow: Modeling Information Flow Towards Human-like Video Captioning","created":"2021-11-19","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":"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":"2401.12419","title":"Multi-modal News Understanding with Professionally Labelled Videos (ReutersViLNews)","created":"2024-01-23","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":"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":"2206.14647","title":"Meta-Wrapper: Differentiable Wrapping Operator for User Interest Selection in CTR Prediction","created":"2022-06-28","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":"2303.07545","title":"Implicit and Explicit Commonsense for Multi-sentence Video Captioning","created":"2023-03-14","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":"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":"2312.13330","title":"Towards Subject-Oriented Video Captioning via User-Specified Targets","created":"2023-12-20","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":"2502.13034","title":"Natural Language Generation from Visual Events: State-of-the-Art and Key Open Questions","created":"2025-02-18","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":"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":"2609.08505","title":"Temporal State Transport in Video Generation: Diagnosing and Correcting Spectral Imbalance","created":"2026-09-08","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":"2210.07076","title":"Few-Shot Visual Question Generation: A Novel Task and Benchmark Datasets","created":"2022-10-13","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":"2312.12721","title":"Cross-Modal Reasoning with Event Correlation for Video Question Answering","created":"2023-12-20","cited_by_count":0,"area":null},{"id":"2403.17013","title":"Temporal-Spatial Processing of Event Camera Data via Delay-Loop Reservoir Neural Network","created":"2024-02-12","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":"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":"2504.16788","title":"Towards Explainable AI: Multi-Modal Transformer for Video-based Image Description Generation","created":"2025-04-23","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":"2508.01270","title":"SGCap: Decoding Semantic Group for Zero-shot Video Captioning","created":"2025-08-02","cited_by_count":0,"area":null},{"id":"2601.08204","title":"MobiDiary: Autoregressive Action Captioning with Wearable Devices and Wireless Signals","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2601.16333","title":"Where is the multimodal goal post? On the Ability of Foundation Models to Recognize Highlights in Videos","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2608.11013","title":"Watching Synthetic Videos: Aligning Cross-modal Representations with Visual Synthesis for Zero-shot Video Captioning","created":"2026-08-11","cited_by_count":0,"area":null}],"next_cursor":null}