{"total":107,"rows":[{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615,"area":"mllm"},{"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":"2104.08541","title":"TransVG: End-to-End Visual Grounding with Transformers","created":"2021-04-17","cited_by_count":271,"area":null},{"id":"2302.14115","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","created":"2023-02-27","cited_by_count":263,"area":"mllm"},{"id":"2305.11846","title":"Any-to-Any Generation via Composable Diffusion","created":"2023-05-19","cited_by_count":204,"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":"2304.08345","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","created":"2023-04-17","cited_by_count":140,"area":null},{"id":"2112.01522","title":"Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks","created":"2021-12-02","cited_by_count":125,"area":null},{"id":"2201.08264","title":"End-to-end Generative Pretraining for Multimodal Video Captioning","created":"2022-01-20","cited_by_count":116,"area":null},{"id":"2204.13101","title":"Self-Supervised Learning of Object Parts for Semantic Segmentation","created":"2022-04-27","cited_by_count":90,"area":null},{"id":"2110.06615","title":"CLIP4Caption: CLIP for Video Caption","created":"2021-10-13","cited_by_count":88,"area":null},{"id":"2204.00679","title":"Learning Audio-Video Modalities from Image Captions","created":"2022-04-01","cited_by_count":80,"area":null},{"id":"2302.00673","title":"ADAPT: Action-aware Driving Caption Transformer","created":"2023-02-01","cited_by_count":78,"area":"driving"},{"id":"2205.13775","title":"A Survey on Long-Tailed Visual Recognition","created":"2022-05-27","cited_by_count":75,"area":null},{"id":"2212.04979","title":"VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners","created":"2022-12-09","cited_by_count":70,"area":null},{"id":"2311.18775","title":"CoDi-2: In-Context, Interleaved, and Interactive Any-to-Any Generation","created":"2023-11-30","cited_by_count":63,"area":"mllm"},{"id":"2108.03679","title":"Joint Inductive and Transductive Learning for Video Object Segmentation","created":"2021-08-08","cited_by_count":61,"area":null},{"id":"2206.04674","title":"Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs","created":"2022-06-09","cited_by_count":58,"area":"moe"},{"id":"2211.11427","title":"Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations","created":"2022-11-21","cited_by_count":57,"area":null},{"id":"2209.13232","title":"A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective","created":"2022-09-27","cited_by_count":56,"area":null},{"id":"2107.12636","title":"Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers","created":"2021-07-27","cited_by_count":49,"area":null},{"id":"2103.05284","title":"Open-book Video Captioning with Retrieve-Copy-Generate Network","created":"2021-03-09","cited_by_count":43,"area":null},{"id":"2108.07948","title":"Learning Conditional Knowledge Distillation for Degraded-Reference Image Quality Assessment","created":"2021-08-18","cited_by_count":41,"area":"distill"},{"id":"2309.13952","title":"VidChapters-7M: Video Chapters at Scale","created":"2023-09-25","cited_by_count":39,"area":null},{"id":"2107.02963","title":"Disentangle Your Dense Object Detector","created":"2021-07-07","cited_by_count":37,"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":"2311.16511","title":"GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generation","created":"2023-11-25","cited_by_count":36,"area":"mllm"},{"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":"2108.07954","title":"Self-Supervised Visual Representations Learning by Contrastive Mask Prediction","created":"2021-08-18","cited_by_count":31,"area":null},{"id":"2203.14040","title":"Visual Abductive Reasoning","created":"2022-03-26","cited_by_count":30,"area":"lr"},{"id":"2303.12423","title":"Text with Knowledge Graph Augmented Transformer for Video Captioning","created":"2023-03-22","cited_by_count":28,"area":null},{"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":"2304.11431","title":"A Review of Deep Learning for Video Captioning","created":"2023-04-22","cited_by_count":28,"area":null},{"id":"2307.07063","title":"Bootstrapping Vision-Language Learning with Decoupled Language Pre-training","created":"2023-07-13","cited_by_count":28,"area":"synth"},{"id":"2203.07112","title":"RCL: Recurrent Continuous Localization for Temporal Action Detection","created":"2022-03-14","cited_by_count":25,"area":null},{"id":"2303.16839","title":"MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks","created":"2023-03-29","cited_by_count":24,"area":null},{"id":"2409.17647","title":"MECD: Unlocking Multi-Event Causal Discovery in Video Reasoning","created":"2024-09-26","cited_by_count":23,"area":"lr"},{"id":"2105.14477","title":"Towards Diverse Paragraph Captioning for Untrimmed Videos","created":"2021-05-30","cited_by_count":22,"area":null},{"id":"2309.12867","title":"Accurate and Fast Compressed Video Captioning","created":"2023-09-22","cited_by_count":22,"area":null},{"id":"2403.17935","title":"OmniVid: A Generative Framework for Universal Video Understanding","created":"2024-03-26","cited_by_count":22,"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":"2112.07515","title":"CoCo-BERT: Improving Video-Language Pre-training with Contrastive Cross-modal Matching and Denoising","created":"2021-12-14","cited_by_count":18,"area":"mllm"},{"id":"2207.08739","title":"Rethinking Data Augmentation for Robust Visual Question Answering","created":"2022-07-18","cited_by_count":18,"area":"distill"},{"id":"2210.12787","title":"Respecting Transfer Gap in Knowledge Distillation","created":"2022-10-23","cited_by_count":18,"area":"distill"},{"id":"2211.15076","title":"Refined Semantic Enhancement towards Frequency Diffusion for Video Captioning","created":"2022-11-28","cited_by_count":18,"area":null},{"id":"2303.06591","title":"Accommodating Audio Modality in CLIP for Multimodal Processing","created":"2023-03-12","cited_by_count":18,"area":"mllm"},{"id":"2303.15616","title":"Fine-grained Audible Video Description","created":"2023-03-27","cited_by_count":18,"area":null},{"id":"2401.06395","title":"ModaVerse: Efficiently Transforming Modalities with LLMs","created":"2024-01-12","cited_by_count":18,"area":null},{"id":"2504.10920","title":"Towards Efficient Partially Relevant Video Retrieval with Active Moment Discovering","created":"2025-04-15","cited_by_count":18,"area":null},{"id":"2106.13266","title":"DnS: Distill-and-Select for Efficient and Accurate Video Indexing and Retrieval","created":"2021-06-24","cited_by_count":17,"area":"distill"},{"id":"2205.10706","title":"GL-RG: Global-Local Representation Granularity for Video Captioning","created":"2022-05-22","cited_by_count":16,"area":null},{"id":"2303.13009","title":"MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models","created":"2023-03-23","cited_by_count":15,"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":"2308.13998","title":"Computation-efficient Deep Learning for Computer Vision: A Survey","created":"2023-08-27","cited_by_count":14,"area":null},{"id":"2208.04897","title":"Sports Video Analysis on Large-Scale Data","created":"2022-08-09","cited_by_count":13,"area":null},{"id":"2301.11507","title":"Semi-Parametric Video-Grounded Text Generation","created":"2023-01-27","cited_by_count":13,"area":null},{"id":"2404.02755","title":"DIBS: Enhancing Dense Video Captioning with Unlabeled Videos via Pseudo Boundary Enrichment and Online Refinement","created":"2024-04-03","cited_by_count":13,"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":"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":"2204.04730","title":"Deep Non-rigid Structure-from-Motion: A Sequence-to-Sequence Translation Perspective","created":"2022-04-10","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":"2409.15196","title":"HOTVCOM: Generating Buzzworthy Comments for Videos","created":"2024-09-23","cited_by_count":7,"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":"2205.06253","title":"What's in a Caption? Dataset-Specific Linguistic Diversity and Its Effect on Visual Description Models and Metrics","created":"2022-05-12","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":"2210.05039","title":"Contrastive Video-Language Learning with Fine-grained Frame Sampling","created":"2022-10-10","cited_by_count":6,"area":null},{"id":"2411.09439","title":"Spider: Any-to-Many Multimodal LLM","created":"2024-11-14","cited_by_count":6,"area":"mllm"},{"id":"2103.14785","title":"A Comprehensive Review of the Video-to-Text Problem","created":"2021-03-27","cited_by_count":5,"area":null},{"id":"2201.04023","title":"Boosting Video Representation Learning with Multi-Faceted Integration","created":"2022-01-11","cited_by_count":5,"area":null},{"id":"2203.16763","title":"CREATE: A Benchmark for Chinese Short Video Retrieval and Title Generation","created":"2022-03-31","cited_by_count":5,"area":null},{"id":"2302.09736","title":"STOA-VLP: Spatial-Temporal Modeling of Object and Action for Video-Language Pre-training","created":"2023-02-20","cited_by_count":5,"area":null},{"id":"2501.07227","title":"MECD+: Unlocking Event-Level Causal Graph Discovery for Video Reasoning","created":"2025-01-13","cited_by_count":5,"area":"lr"},{"id":"2108.06458","title":"Cross-Modal Graph with Meta Concepts for Video Captioning","created":"2021-08-14","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":"2312.15720","title":"Set Prediction Guided by Semantic Concepts for Diverse Video Captioning","created":"2023-12-25","cited_by_count":4,"area":null},{"id":"2506.21188","title":"GroundFlow: A Plug-in Module for Temporal Reasoning on 3D Point Cloud Sequential Grounding","created":"2025-06-26","cited_by_count":4,"area":"lr"},{"id":"2203.06356","title":"Taking an Emotional Look at Video Paragraph Captioning","created":"2022-03-12","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":"2304.02080","title":"Scalable and Accurate Self-supervised Multimodal Representation Learning without Aligned Video and Text Data","created":"2023-04-04","cited_by_count":3,"area":null},{"id":"2305.03204","title":"VideoOFA: Two-Stage Pre-Training for Video-to-Text Generation","created":"2023-05-04","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":"2112.14088","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":"2208.09266","title":"Diverse Video Captioning by Adaptive Spatio-temporal Attention","created":"2022-08-19","cited_by_count":2,"area":null},{"id":"2411.04059","title":"Pseudo-labeling with Keyword Refining for Few-Supervised Video Captioning","created":"2024-11-06","cited_by_count":2,"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":"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":"2312.06699","title":"Leveraging Generative Language Models for Weakly Supervised Sentence Component Analysis in Video-Language Joint Learning","created":"2023-12-10","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":"2204.13548","title":"Tragedy Plus Time: Capturing Unintended Human Activities from Weakly-labeled Videos","created":"2022-04-28","cited_by_count":0,"area":null},{"id":"2205.09307","title":"Support-set based Multi-modal Representation Enhancement for Video Captioning","created":"2022-05-19","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":"2401.04354","title":"Knowledge-enhanced Multi-perspective Video Representation Learning for Scene Recognition","created":"2024-01-09","cited_by_count":0,"area":null}],"next_cursor":"100"}