{"total":158,"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":"2207.01696","title":"TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts","created":"2022-07-04","cited_by_count":359,"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":"2312.03718","title":"Large Language Models in Law: A Survey","created":"2023-11-26","cited_by_count":128,"area":null},{"id":"2402.11435","title":"Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning","created":"2024-02-18","cited_by_count":122,"area":"lr"},{"id":"2108.03353","title":"Screen2Words: Automatic Mobile UI Summarization with Multimodal Learning","created":"2021-08-07","cited_by_count":120,"area":null},{"id":"2402.10828","title":"RAG-Driver: Generalisable Driving Explanations with Retrieval-Augmented In-Context Learning in Multi-Modal Large Language Model","created":"2024-02-16","cited_by_count":92,"area":"mllm"},{"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":"2104.08271","title":"TEACHTEXT: CrossModal Generalized Distillation for Text-Video Retrieval","created":"2021-04-16","cited_by_count":81,"area":null},{"id":"2302.00673","title":"ADAPT: Action-aware Driving Caption Transformer","created":"2023-02-01","cited_by_count":78,"area":"driving"},{"id":"2112.12777","title":"Cross Modal Retrieval with Querybank Normalisation","created":"2021-12-23","cited_by_count":72,"area":null},{"id":"2105.06247","title":"Video Corpus Moment Retrieval with Contrastive Learning","created":"2021-05-13","cited_by_count":60,"area":null},{"id":"2108.08121","title":"Target Adaptive Context Aggregation for Video Scene Graph Generation","created":"2021-08-18","cited_by_count":52,"area":null},{"id":"2406.02965","title":"Understanding the Impact of Negative Prompts: When and How Do They Take Effect?","created":"2024-06-05","cited_by_count":51,"area":"diffusion"},{"id":"2303.16899","title":"AutoAD: Movie Description in Context","created":"2023-03-29","cited_by_count":50,"area":null},{"id":"2102.05150","title":"RODNet: A Real-Time Radar Object Detection Network Cross-Supervised by Camera-Radar Fused Object 3D Localization","created":"2021-02-09","cited_by_count":49,"area":null},{"id":"2103.10095","title":"On Semantic Similarity in Video Retrieval","created":"2021-03-18","cited_by_count":46,"area":null},{"id":"2103.16057","title":"Grounding Open-Domain Instructions to Automate Web Support Tasks","created":"2021-03-30","cited_by_count":43,"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":"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":"2111.08919","title":"EMScore: Evaluating Video Captioning via Coarse-Grained and Fine-Grained Embedding Matching","created":"2021-11-17","cited_by_count":36,"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":"2105.04066","title":"Reconstructive Sequence-Graph Network for Video Summarization","created":"2021-05-10","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":"2203.14040","title":"Visual Abductive Reasoning","created":"2022-03-26","cited_by_count":30,"area":"lr"},{"id":"2303.14655","title":"GOAL: A Challenging Knowledge-grounded Video Captioning Benchmark for Real-time Soccer Commentary Generation","created":"2023-03-26","cited_by_count":28,"area":null},{"id":"2107.02248","title":"A comparison of LSTM and GRU networks for learning symbolic sequences","created":"2021-07-05","cited_by_count":24,"area":null},{"id":"2105.14477","title":"Towards Diverse Paragraph Captioning for Untrimmed Videos","created":"2021-05-30","cited_by_count":22,"area":null},{"id":"1708.02300","title":"Reinforced Video Captioning with Entailment Rewards","created":"2017-08-07","cited_by_count":21,"area":"alignment"},{"id":"2410.01806","title":"Samba: Synchronized Set-of-Sequences Modeling for Multiple Object Tracking","created":"2024-10-02","cited_by_count":21,"area":null},{"id":"2207.11441","title":"Meta Spatio-Temporal Debiasing for Video Scene Graph Generation","created":"2022-07-23","cited_by_count":20,"area":null},{"id":"2303.02961","title":"Models See Hallucinations: Evaluating the Factuality in Video Captioning","created":"2023-03-06","cited_by_count":19,"area":null},{"id":"2107.12270","title":"Adaptive Hierarchical Graph Reasoning with Semantic Coherence for Video-and-Language Inference","created":"2021-07-26","cited_by_count":18,"area":null},{"id":"2210.08714","title":"Selective Query-guided Debiasing for Video Corpus Moment Retrieval","created":"2022-10-17","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":"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":"2501.00226","title":"Generative Emergent Communication: Large Language Model is a Collective World Model","created":"2024-12-31","cited_by_count":15,"area":"wm"},{"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":"2308.04782","title":"PointMBF: A Multi-scale Bidirectional Fusion Network for Unsupervised RGB-D Point Cloud Registration","created":"2023-08-09","cited_by_count":14,"area":null},{"id":"2403.13507","title":"FMM-Attack: A Flow-based Multi-modal Adversarial Attack on Video-based LLMs","created":"2024-03-20","cited_by_count":14,"area":null},{"id":"2110.03389","title":"Beam Search with Bidirectional Strategies for Neural Response Generation","created":"2021-10-07","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":"2407.18589","title":"HICEScore: A Hierarchical Metric for Image Captioning Evaluation","created":"2024-07-26","cited_by_count":12,"area":null},{"id":"2107.12600","title":"PiSLTRc: Position-informed Sign Language Transformer with Content-aware Convolution","created":"2021-07-27","cited_by_count":11,"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":"2204.08123","title":"Non-Parallel Text Style Transfer with Self-Parallel Supervision","created":"2022-04-18","cited_by_count":11,"area":null},{"id":"2205.10195","title":"Unsupervised Flow-Aligned Sequence-to-Sequence Learning for Video Restoration","created":"2022-05-20","cited_by_count":11,"area":null},{"id":"2503.13957","title":"DIFFVSGG: Diffusion-Driven Online Video Scene Graph Generation","created":"2025-03-18","cited_by_count":11,"area":null},{"id":"2110.11298","title":"Video and Text Matching with Conditioned Embeddings","created":"2021-10-21","cited_by_count":10,"area":null},{"id":"2207.12571","title":"Innovations in Neural Data-to-text Generation: A Survey","created":"2022-07-25","cited_by_count":10,"area":null},{"id":"2404.15349","title":"A Survey on Multimodal Wearable Sensor-based Human Action Recognition","created":"2024-04-14","cited_by_count":10,"area":null},{"id":"2406.06499","title":"NarrativeBridge: Enhancing Video Captioning with Causal-Temporal Narrative","created":"2024-06-10","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":"2405.11483","title":"MICap: A Unified Model for Identity-aware Movie Descriptions","created":"2024-05-19","cited_by_count":9,"area":null},{"id":"2410.20034","title":"Sensor2Text: Enabling Natural Language Interactions for Daily Activity Tracking Using Wearable Sensors","created":"2024-10-26","cited_by_count":9,"area":null},{"id":"2412.14056","title":"A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future","created":"2024-12-18","cited_by_count":9,"area":null},{"id":"2110.15609","title":"BiC-Net: Learning Efficient Spatio-Temporal Relation for Text-Video Retrieval","created":"2021-10-29","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":"2606.09393","title":"CapRL++: Unified Reinforcement Learning with Verifiable Rewards for Dense Image and Video Captioning","created":"2026-06-08","cited_by_count":8,"area":"mllm"},{"id":"2103.14517","title":"On the hidden treasure of dialog in video question answering","created":"2021-03-26","cited_by_count":7,"area":null},{"id":"2108.03662","title":"Discriminative Latent Semantic Graph for Video Captioning","created":"2021-08-08","cited_by_count":7,"area":null},{"id":"2407.02411","title":"Video Watermarking: Safeguarding Your Video from (Unauthorized) Annotations by Video-based LLMs","created":"2024-07-02","cited_by_count":7,"area":"safety"},{"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":"2209.07518","title":"Distribution Aware Metrics for Conditional Natural Language Generation","created":"2022-09-15","cited_by_count":6,"area":null},{"id":"2303.14829","title":"SEM-POS: Grammatically and Semantically Correct Video Captioning","created":"2023-03-26","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":"2402.10534","title":"Using Left and Right Brains Together: Towards Vision and Language Planning","created":"2024-02-16","cited_by_count":6,"area":null},{"id":"2404.17498","title":"Learning text-to-video retrieval from image captioning","created":"2024-04-26","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":"2207.11842","title":"$\\textit{FastSVD-ML-ROM}$: A Reduced-Order Modeling Framework based on Machine Learning for Real-Time Applications","created":"2022-07-24","cited_by_count":5,"area":null},{"id":"2210.10820","title":"VTC: Improving Video-Text Retrieval with User Comments","created":"2022-10-19","cited_by_count":5,"area":null},{"id":"2501.04302","title":"H-MBA: Hierarchical MamBa Adaptation for Multi-Modal Video Understanding in Autonomous Driving","created":"2025-01-08","cited_by_count":5,"area":"mllm"},{"id":"2507.12841","title":"AnyCap Project: A Unified Framework, Dataset, and Benchmark for Controllable Omni-modal Captioning","created":"2025-07-17","cited_by_count":5,"area":null},{"id":"2510.18054","title":"HouseTour: A Virtual Real Estate A(I)gent","created":"2025-10-20","cited_by_count":5,"area":null},{"id":"2108.02365","title":"Hybrid Reasoning Network for Video-based Commonsense Captioning","created":"2021-08-05","cited_by_count":4,"area":null},{"id":"2201.06734","title":"Cross-modal Contrastive Distillation for Instructional Activity Anticipation","created":"2022-01-18","cited_by_count":4,"area":"distill"},{"id":"2211.09469","title":"Visual Commonsense-aware Representation Network for Video Captioning","created":"2022-11-17","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":"2504.02286","title":"Moment Quantization for Video Temporal Grounding","created":"2025-04-03","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":"2204.07047","title":"State of the Art in Artificial Intelligence applied to the Legal Domain","created":"2022-03-10","cited_by_count":3,"area":null},{"id":"2205.03534","title":"Attract me to Buy: Advertisement Copywriting Generation with Multimodal Multi-structured Information","created":"2022-05-07","cited_by_count":3,"area":null},{"id":"2208.11553","title":"MuMUR : Multilingual Multimodal Universal Retrieval","created":"2022-08-24","cited_by_count":3,"area":"mllm"},{"id":"2305.08389","title":"Edit As You Wish: Video Caption Editing with Multi-grained User Control","created":"2023-05-15","cited_by_count":3,"area":null},{"id":"2306.11341","title":"MSVD-Indonesian: A Benchmark for Multimodal Video-Text Tasks in Indonesian","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2401.02052","title":"Encoder-Decoder Based Long Short-Term Memory (LSTM) Model for Video Captioning","created":"2023-10-02","cited_by_count":3,"area":null},{"id":"2410.09379","title":"Multi-granularity Contrastive Cross-modal Collaborative Generation for End-to-End Long-term Video Question Answering","created":"2024-10-12","cited_by_count":3,"area":null},{"id":"2412.11467","title":"Exploring Temporal Event Cues for Dense Video Captioning in Cyclic Co-learning","created":"2024-12-16","cited_by_count":3,"area":null},{"id":"2503.24096","title":"DANTE-AD: Dual-Vision Attention Network for Long-Term Audio Description","created":"2025-03-31","cited_by_count":3,"area":null},{"id":"2505.23751","title":"REOrdering Patches Improves Vision Models","created":"2025-05-29","cited_by_count":3,"area":null},{"id":"2510.04428","title":"A.I.R.: Enabling Adaptive, Iterative, and Reasoning-based Frame Selection For Video Question Answering","created":"2025-10-06","cited_by_count":3,"area":"lr"},{"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}],"next_cursor":"100"}