{"total":95,"rows":[{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"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":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"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":"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":"2105.09996","title":"VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding","created":"2021-05-20","cited_by_count":102,"area":null},{"id":"2203.16434","title":"TubeDETR: Spatio-Temporal Video Grounding with Transformers","created":"2022-03-30","cited_by_count":98,"area":null},{"id":"2103.15049","title":"HiT: Hierarchical Transformer with Momentum Contrast for Video-Text Retrieval","created":"2021-03-28","cited_by_count":87,"area":null},{"id":"2207.00419","title":"Self-Supervised Learning for Videos: A Survey","created":"2022-06-18","cited_by_count":85,"area":null},{"id":"2201.04850","title":"Bridging Video-text Retrieval with Multiple Choice Questions","created":"2022-01-13","cited_by_count":79,"area":null},{"id":"2109.14910","title":"CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video Representations","created":"2021-09-30","cited_by_count":72,"area":null},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66,"area":null},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"area":null},{"id":"2210.06031","title":"Long-Form Video-Language Pre-Training with Multimodal Temporal Contrastive Learning","created":"2022-10-12","cited_by_count":59,"area":null},{"id":"2401.02309","title":"TR-DETR: Task-Reciprocal Transformer for Joint Moment Retrieval and Highlight Detection","created":"2024-01-04","cited_by_count":59,"area":null},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58,"area":null},{"id":"2307.02869","title":"MomentDiff: Generative Video Moment Retrieval from Random to Real","created":"2023-07-06","cited_by_count":58,"area":null},{"id":"2301.02074","title":"Test of Time: Instilling Video-Language Models with a Sense of Time","created":"2023-01-05","cited_by_count":51,"area":null},{"id":"2306.07520","title":"Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions","created":"2023-06-13","cited_by_count":46,"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":"2209.13306","title":"Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding","created":"2022-09-27","cited_by_count":42,"area":null},{"id":"2112.07175","title":"Co-training Transformer with Videos and Images Improves Action Recognition","created":"2021-12-14","cited_by_count":41,"area":null},{"id":"2207.07885","title":"Clover: Towards A Unified Video-Language Alignment and Fusion Model","created":"2022-07-16","cited_by_count":41,"area":null},{"id":"2208.14882","title":"Hierarchical Local-Global Transformer for Temporal Sentence Grounding","created":"2022-08-31","cited_by_count":38,"area":null},{"id":"2307.08763","title":"Video-Mined Task Graphs for Keystep Recognition in Instructional Videos","created":"2023-07-17","cited_by_count":35,"area":null},{"id":"2201.09168","title":"Reading-strategy Inspired Visual Representation Learning for Text-to-Video Retrieval","created":"2022-01-23","cited_by_count":34,"area":null},{"id":"2211.16761","title":"Improving Cross-Modal Retrieval with Set of Diverse Embeddings","created":"2022-11-30","cited_by_count":33,"area":null},{"id":"2107.12059","title":"HANet: Hierarchical Alignment Networks for Video-Text Retrieval","created":"2021-07-26","cited_by_count":31,"area":null},{"id":"2204.12408","title":"MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval","created":"2022-04-26","cited_by_count":29,"area":null},{"id":"2303.12423","title":"Text with Knowledge Graph Augmented Transformer for Video Captioning","created":"2023-03-22","cited_by_count":28,"area":null},{"id":"2306.03802","title":"Learning to Ground Instructional Articles in Videos through Narrations","created":"2023-06-06","cited_by_count":28,"area":null},{"id":"2211.15103","title":"VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning","created":"2022-11-28","cited_by_count":25,"area":null},{"id":"2111.12890","title":"V2C: Visual Voice Cloning","created":"2021-11-25","cited_by_count":24,"area":null},{"id":"2203.16784","title":"Video-Text Representation Learning via Differentiable Weak Temporal Alignment","created":"2022-03-31","cited_by_count":24,"area":null},{"id":"2104.09411","title":"Understanding Chinese Video and Language via Contrastive Multimodal Pre-Training","created":"2021-04-19","cited_by_count":23,"area":null},{"id":"2111.01300","title":"Masking Modalities for Cross-modal Video Retrieval","created":"2021-11-01","cited_by_count":23,"area":null},{"id":"2207.02159","title":"Robustness Analysis of Video-Language Models Against Visual and Language Perturbations","created":"2022-07-05","cited_by_count":23,"area":null},{"id":"2308.11488","title":"Opening the Vocabulary of Egocentric Actions","created":"2023-08-22","cited_by_count":23,"area":null},{"id":"2307.12964","title":"Audio-Enhanced Text-to-Video Retrieval using Text-Conditioned Feature Alignment","created":"2023-07-24","cited_by_count":21,"area":null},{"id":"2203.08543","title":"Integrating Language Guidance into Vision-based Deep Metric Learning","created":"2022-03-16","cited_by_count":19,"area":null},{"id":"2206.12972","title":"VLCap: Vision-Language with Contrastive Learning for Coherent Video Paragraph Captioning","created":"2022-06-26","cited_by_count":19,"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":"2205.06160","title":"Localized Vision-Language Matching for Open-vocabulary Object Detection","created":"2022-05-12","cited_by_count":17,"area":null},{"id":"2109.09487","title":"Dyadformer: A Multi-modal Transformer for Long-Range Modeling of Dyadic Interactions","created":"2021-09-20","cited_by_count":16,"area":null},{"id":"2111.01705","title":"AI Ethics Statements -- Analysis and lessons learnt from NeurIPS Broader Impact Statements","created":"2021-11-02","cited_by_count":16,"area":null},{"id":"2212.13738","title":"TempCLR: Temporal Alignment Representation with Contrastive Learning","created":"2022-12-28","cited_by_count":15,"area":null},{"id":"2302.12552","title":"Deep Learning for Video-Text Retrieval: a Review","created":"2023-02-24","cited_by_count":15,"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":"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":"2107.11851","title":"Transcript to Video: Efficient Clip Sequencing from Texts","created":"2021-07-25","cited_by_count":13,"area":null},{"id":"2111.09276","title":"Induce, Edit, Retrieve: Language Grounded Multimodal Schema for Instructional Video Retrieval","created":"2021-11-17","cited_by_count":13,"area":null},{"id":"2203.07086","title":"MDMMT-2: Multidomain Multimodal Transformer for Video Retrieval, One More Step Towards Generalization","created":"2022-03-14","cited_by_count":10,"area":null},{"id":"2311.14315","title":"Robust Domain Misinformation Detection via Multi-modal Feature Alignment","created":"2023-11-24","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":"2310.16639","title":"Driving through the Concept Gridlock: Unraveling Explainability Bottlenecks in Automated Driving","created":"2023-10-25","cited_by_count":9,"area":null},{"id":"2504.13112","title":"Hadamard product in deep learning: Introduction, Advances and Challenges","created":"2025-04-17","cited_by_count":9,"area":null},{"id":"2106.07550","title":"Attention mechanisms and deep learning for machine vision: A survey of the state of the art","created":"2021-06-03","cited_by_count":8,"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":"2202.03384","title":"Hybrid Contrastive Quantization for Efficient Cross-View Video Retrieval","created":"2022-02-07","cited_by_count":8,"area":null},{"id":"2303.06378","title":"Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos","created":"2023-03-11","cited_by_count":8,"area":null},{"id":"2407.07478","title":"EA-VTR: Event-Aware Video-Text Retrieval","created":"2024-07-10","cited_by_count":8,"area":null},{"id":"2104.00285","title":"CUPID: Adaptive Curation of Pre-training Data for Video-and-Language Representation Learning","created":"2021-04-01","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":"2210.08164","title":"Linear Video Transformer with Feature Fixation","created":"2022-10-15","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":"2203.13291","title":"Searching for fingerspelled content in American Sign Language","created":"2022-03-24","cited_by_count":5,"area":null},{"id":"2212.06206","title":"Contextual Explainable Video Representation: Human Perception-based Understanding","created":"2022-12-12","cited_by_count":5,"area":null},{"id":"2405.17790","title":"Instruct-ReID++: Towards Universal Purpose Instruction-Guided Person Re-identification","created":"2024-05-28","cited_by_count":5,"area":null},{"id":"2507.00033","title":"Moment Sampling in Video LLMs for Long-Form Video QA","created":"2025-06-18","cited_by_count":5,"area":null},{"id":"2112.12182","title":"Fine-grained Multi-Modal Self-Supervised Learning","created":"2021-12-22","cited_by_count":4,"area":null},{"id":"2210.16431","title":"DiMBERT: Learning Vision-Language Grounded Representations with Disentangled Multimodal-Attention","created":"2022-10-28","cited_by_count":4,"area":null},{"id":"2402.13566","title":"Event-aware Video Corpus Moment Retrieval","created":"2024-02-21","cited_by_count":4,"area":null},{"id":"2204.08209","title":"OMG: Observe Multiple Granularities for Natural Language-Based Vehicle Retrieval","created":"2022-04-18","cited_by_count":3,"area":null},{"id":"2209.11870","title":"Leveraging Self-Supervised Training for Unintentional Action Recognition","created":"2022-09-23","cited_by_count":3,"area":null},{"id":"2210.04341","title":"ConTra: (Con)text (Tra)nsformer for Cross-Modal Video Retrieval","created":"2022-10-09","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":"2306.14460","title":"Hierarchical Matching and Reasoning for Multi-Query Image Retrieval","created":"2023-06-26","cited_by_count":3,"area":null},{"id":"2403.19221","title":"Towards Multimodal Video Paragraph Captioning Models Robust to Missing Modality","created":"2024-03-28","cited_by_count":3,"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":"2207.09083","title":"Relational Future Captioning Model for Explaining Likely Collisions in Daily Tasks","created":"2022-07-19","cited_by_count":2,"area":null},{"id":"2308.12419","title":"Toward American Sign Language Processing in the Real World: Data, Tasks, and Methods","created":"2023-08-23","cited_by_count":1,"area":null},{"id":"2309.13607","title":"MM-NeRF: Multimodal-Guided 3D Multi-Style Transfer of Neural Radiance Field","created":"2023-09-24","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":"2402.02335","title":"Video Editing for Video Retrieval","created":"2024-02-04","cited_by_count":1,"area":null},{"id":"2505.16425","title":"$I^2G$: Generating Instructional Illustrations via Text-Conditioned Diffusion","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2505.23952","title":"Leveraging Auxiliary Information in Text-to-Video Retrieval: A Review","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2608.07993","title":"MRBench: A Comprehensive Benchmark for Human Motion-Text Retrieval","created":"2026-08-08","cited_by_count":1,"area":null},{"id":"2204.10938","title":"A Multi-level Alignment Training Scheme for Video-and-Language Grounding","created":"2022-04-22","cited_by_count":0,"area":null},{"id":"2212.03864","title":"Can Offline Reinforcement Learning Help Natural Language Understanding?","created":"2022-09-15","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":"2403.01615","title":"Partial Federated Learning","created":"2024-03-03","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":"2406.13809","title":"Towards Holistic Language-video Representation: the language model-enhanced MSR-Video to Text Dataset","created":"2024-06-19","cited_by_count":0,"area":null},{"id":"2410.09377","title":"GEM-VPC: A dual Graph-Enhanced Multimodal integration for Video Paragraph Captioning","created":"2024-10-12","cited_by_count":0,"area":null},{"id":"2609.24031","title":"Video-STLayout Pre-training","created":"2026-09-21","cited_by_count":0,"area":null}],"next_cursor":null}