{"total":93,"rows":[{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629,"area":null},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2206.01670","title":"Egocentric Video-Language Pretraining","created":"2022-06-03","cited_by_count":232,"area":null},{"id":"2305.00976","title":"TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis","created":"2023-05-02","cited_by_count":198,"area":null},{"id":"2305.17390","title":"SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks","created":"2023-05-27","cited_by_count":168,"area":"lr"},{"id":"2209.07526","title":"OmniVL:One Foundation Model for Image-Language and Video-Language Tasks","created":"2022-09-15","cited_by_count":143,"area":null},{"id":"2303.12501","title":"Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval","created":"2023-03-22","cited_by_count":132,"area":"lr"},{"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":"2412.01720","title":"LamRA: Large Multimodal Model as Your Advanced Retrieval Assistant","created":"2024-12-02","cited_by_count":106,"area":"mllm"},{"id":"2204.02968","title":"Temporal Alignment Networks for Long-term Video","created":"2022-04-06","cited_by_count":84,"area":null},{"id":"2203.08101","title":"ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity","created":"2022-03-15","cited_by_count":83,"area":null},{"id":"2109.06082","title":"xGQA: Cross-Lingual Visual Question Answering","created":"2021-09-13","cited_by_count":72,"area":null},{"id":"2112.12777","title":"Cross Modal Retrieval with Querybank Normalisation","created":"2021-12-23","cited_by_count":72,"area":null},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"area":null},{"id":"2310.16755","title":"HI-TOM: A Benchmark for Evaluating Higher-Order Theory of Mind Reasoning in Large Language Models","created":"2023-10-25","cited_by_count":63,"area":"lr"},{"id":"2205.08508","title":"A CLIP-Hitchhiker's Guide to Long Video Retrieval","created":"2022-05-17","cited_by_count":57,"area":null},{"id":"2203.14713","title":"Image-text Retrieval: A Survey on Recent Research and Development","created":"2022-03-28","cited_by_count":55,"area":null},{"id":"2306.01879","title":"Revisiting the Role of Language Priors in Vision-Language Models","created":"2023-06-02","cited_by_count":50,"area":"mllm"},{"id":"2204.05626","title":"X-DETR: A Versatile Architecture for Instance-wise Vision-Language Tasks","created":"2022-04-12","cited_by_count":43,"area":null},{"id":"2203.09773","title":"Local-Global Context Aware Transformer for Language-Guided Video Segmentation","created":"2022-03-18","cited_by_count":41,"area":null},{"id":"2303.11607","title":"Transformers in Speech Processing: A Survey","created":"2023-03-21","cited_by_count":39,"area":null},{"id":"2211.09623","title":"Cross-Modal Adapter for Vision-Language Retrieval","created":"2022-11-17","cited_by_count":35,"area":null},{"id":"2509.12662","title":"Chat-Driven Text Generation and Interaction for Person Retrieval","created":"2025-09-16","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":"2203.16778","title":"ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval","created":"2022-03-31","cited_by_count":29,"area":null},{"id":"2203.15867","title":"Image Retrieval from Contextual Descriptions","created":"2022-03-29","cited_by_count":26,"area":null},{"id":"2202.07247","title":"CommerceMM: Large-Scale Commerce MultiModal Representation Learning with Omni Retrieval","created":"2022-02-15","cited_by_count":25,"area":null},{"id":"2109.08186","title":"Fast-Slow Transformer for Visually Grounding Speech","created":"2021-09-16","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":"2112.08723","title":"Distilled Dual-Encoder Model for Vision-Language Understanding","created":"2021-12-16","cited_by_count":22,"area":null},{"id":"2208.12526","title":"Cross-Lingual Cross-Modal Retrieval with Noise-Robust Learning","created":"2022-08-26","cited_by_count":22,"area":null},{"id":"2311.00519","title":"REBAR: Retrieval-Based Reconstruction for Time-series Contrastive Learning","created":"2023-11-01","cited_by_count":21,"area":null},{"id":"2203.14804","title":"Partially Does It: Towards Scene-Level FG-SBIR with Partial Input","created":"2022-03-28","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":"2310.07265","title":"Distilling Efficient Vision Transformers from CNNs for Semantic Segmentation","created":"2023-10-11","cited_by_count":18,"area":"distill"},{"id":"2411.16752","title":"Imagine and Seek: Improving Composed Image Retrieval with an Imagined Proxy","created":"2024-11-24","cited_by_count":18,"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":"2208.00934","title":"Video Question Answering with Iterative Video-Text Co-Tokenization","created":"2022-08-01","cited_by_count":16,"area":null},{"id":"2303.17644","title":"Vision-Language Modelling For Radiological Imaging and Reports In The Low Data Regime","created":"2023-03-30","cited_by_count":15,"area":"mllm"},{"id":"2305.16397","title":"Are Diffusion Models Vision-And-Language Reasoners?","created":"2023-05-25","cited_by_count":14,"area":"lr"},{"id":"2306.02092","title":"Collaborative Group: Composed Image Retrieval via Consensus Learning from Noisy Annotations","created":"2023-06-03","cited_by_count":14,"area":null},{"id":"2505.06566","title":"Dynamic Uncertainty Learning with Noisy Correspondence for Text-Based Person Search","created":"2025-05-10","cited_by_count":11,"area":null},{"id":"2306.08789","title":"Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training","created":"2023-06-15","cited_by_count":10,"area":null},{"id":"2106.02253","title":"X-volution: On the unification of convolution and self-attention","created":"2021-06-04","cited_by_count":9,"area":null},{"id":"2109.12564","title":"Vision Transformer Hashing for Image Retrieval","created":"2021-09-26","cited_by_count":9,"area":null},{"id":"2203.05465","title":"LoopITR: Combining Dual and Cross Encoder Architectures for Image-Text Retrieval","created":"2022-03-10","cited_by_count":9,"area":null},{"id":"2502.15682","title":"ELIP: Enhanced Visual-Language Foundation Models for Image Retrieval","created":"2025-02-21","cited_by_count":9,"area":null},{"id":"2207.02334","title":"Weakly Supervised Grounding for VQA in Vision-Language Transformers","created":"2022-07-05","cited_by_count":8,"area":null},{"id":"2308.14009","title":"Towards Fast and Accurate Image-Text Retrieval with Self-Supervised Fine-Grained Alignment","created":"2023-08-27","cited_by_count":8,"area":null},{"id":"2301.01702","title":"Automating Nearest Neighbor Search Configuration with Constrained Optimization","created":"2023-01-04","cited_by_count":7,"area":null},{"id":"2303.14333","title":"Train/Test-Time Adaptation with Retrieval","created":"2023-03-25","cited_by_count":7,"area":null},{"id":"2312.04552","title":"Generating Illustrated Instructions","created":"2023-12-07","cited_by_count":7,"area":null},{"id":"2505.08189","title":"DSADF: Thinking Fast and Slow for Decision Making","created":"2025-05-13","cited_by_count":7,"area":"lr"},{"id":"2603.02929","title":"TRACE: Task-Adaptive Reasoning and Representation Learning for Universal Multimodal Retrieval","created":"2026-03-03","cited_by_count":7,"area":"lr"},{"id":"2110.12812","title":"Domain Adaptation in Multi-View Embedding for Cross-Modal Video Retrieval","created":"2021-10-25","cited_by_count":6,"area":null},{"id":"2204.09730","title":"Transformer Decoders with MultiModal Regularization for Cross-Modal Food Retrieval","created":"2022-04-20","cited_by_count":6,"area":null},{"id":"2208.12587","title":"Mitosis Detection, Fast and Slow: Robust and Efficient Detection of Mitotic Figures","created":"2022-08-26","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":"2211.10147","title":"FiE: Building a Global Probability Space by Leveraging Early Fusion in Encoder for Open-Domain Question Answering","created":"2022-11-18","cited_by_count":5,"area":null},{"id":"2301.02307","title":"What You Say Is What You Show: Visual Narration Detection in Instructional Videos","created":"2023-01-05","cited_by_count":5,"area":null},{"id":"2303.06329","title":"MetaViewer: Towards A Unified Multi-View Representation","created":"2023-03-11","cited_by_count":5,"area":null},{"id":"2309.08928","title":"In-Style: Bridging Text and Uncurated Videos with Style Transfer for Text-Video Retrieval","created":"2023-09-16","cited_by_count":5,"area":"mllm"},{"id":"2310.14909","title":"Linking Surface Facts to Large-Scale Knowledge Graphs","created":"2023-10-23","cited_by_count":5,"area":null},{"id":"2312.00414","title":"Vision-Language Models Learn Super Images for Efficient Partially Relevant Video Retrieval","created":"2023-12-01","cited_by_count":5,"area":"mllm"},{"id":"2505.15877","title":"Highlighting What Matters: Promptable Embeddings for Attribute-Focused Image Retrieval","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2110.07811","title":"Cascaded Fast and Slow Models for Efficient Semantic Code Search","created":"2021-10-15","cited_by_count":4,"area":null},{"id":"2111.05814","title":"SwAMP: Swapped Assignment of Multi-Modal Pairs for Cross-Modal Retrieval","created":"2021-11-10","cited_by_count":4,"area":null},{"id":"2201.02772","title":"A Comprehensive Empirical Study of Vision-Language Pre-trained Model for Supervised Cross-Modal Retrieval","created":"2022-01-08","cited_by_count":4,"area":"mllm"},{"id":"2210.10486","title":"Cross-Modal Fusion Distillation for Fine-Grained Sketch-Based Image Retrieval","created":"2022-10-19","cited_by_count":4,"area":null},{"id":"2310.13276","title":"InvGC: Robust Cross-Modal Retrieval by Inverse Graph Convolution","created":"2023-10-20","cited_by_count":4,"area":null},{"id":"2311.15564","title":"Boot and Switch: Alternating Distillation for Zero-Shot Dense Retrieval","created":"2023-11-27","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":"2407.07479","title":"How to Make Cross Encoder a Good Teacher for Efficient Image-Text Retrieval?","created":"2024-07-10","cited_by_count":4,"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":"2507.10195","title":"Minimizing the Pretraining Gap: Domain-aligned Text-Based Person Retrieval","created":"2025-07-14","cited_by_count":3,"area":null},{"id":"2509.08897","title":"Recurrence Meets Transformers for Universal Multimodal Retrieval","created":"2025-09-10","cited_by_count":3,"area":"mllm"},{"id":"2510.12283","title":"Dual Learning with Dynamic Knowledge Distillation and Soft Alignment for Partially Relevant Video Retrieval","created":"2025-10-14","cited_by_count":3,"area":"distill"},{"id":"2511.13415","title":"Attention Grounded Enhancement for Visual Document Retrieval","created":"2025-11-17","cited_by_count":3,"area":null},{"id":"2301.04742","title":"HADA: A Graph-based Amalgamation Framework in Image-text Retrieval","created":"2023-01-11","cited_by_count":2,"area":null},{"id":"2307.09059","title":"Text-guided Image Restoration and Semantic Enhancement for Text-to-Image Person Retrieval","created":"2023-07-18","cited_by_count":2,"area":null},{"id":"2307.09972","title":"Fine-grained Text-Video Retrieval with Frozen Image Encoders","created":"2023-07-14","cited_by_count":2,"area":null},{"id":"2304.07593","title":"Teacher Network Calibration Improves Cross-Quality Knowledge Distillation","created":"2023-04-15","cited_by_count":1,"area":"distill"},{"id":"2310.19654","title":"MCAD: Multi-teacher Cross-modal Alignment Distillation for efficient image-text retrieval","created":"2023-10-30","cited_by_count":1,"area":null},{"id":"2506.21538","title":"Maximal Matching Matters: Preventing Representation Collapse for Robust Cross-Modal Retrieval","created":"2025-06-26","cited_by_count":1,"area":null},{"id":"2509.16560","title":"Captioning for Text-Video Retrieval via Dual-Group Direct Preference Optimization","created":"2025-09-20","cited_by_count":1,"area":"alignment"},{"id":"2303.07740","title":"Efficient Image-Text Retrieval via Keyword-Guided Pre-Screening","created":"2023-03-14","cited_by_count":0,"area":null},{"id":"2305.00715","title":"ZeroSearch: Local Image Search from Text with Zero Shot Learning","created":"2023-05-01","cited_by_count":0,"area":null},{"id":"2309.06176","title":"Dual-Path Temporal Map Optimization for Make-up Temporal Video Grounding","created":"2023-09-12","cited_by_count":0,"area":null},{"id":"2407.19812","title":"Image-text matching for large-scale book collections","created":"2024-07-29","cited_by_count":0,"area":null},{"id":"2601.22929","title":"Semantic Leakage from Image Embeddings","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2604.09114","title":"FIRE-CIR: Fine-grained Reasoning for Composed Fashion Image Retrieval","created":"2026-04-10","cited_by_count":0,"area":"lr"},{"id":"2609.10008","title":"Beyond Similarity: Foundation Models as an Efficient Backbone for Training-Free Composed Video Retrieval","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.27142","title":"MINER: Multi-crop INference-time Enhancement for Rare-Object Retrieval with Frozen Dual Encoders","created":"2026-09-22","cited_by_count":0,"area":null}],"next_cursor":null}