{"list":"other","total":52,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"2108.04024","title":"Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models","created":"2021-08-09","cited_by_count":251},{"id":"1812.07119","title":"Composing Text and Image for Image Retrieval - An Empirical Odyssey","created":"2018-12-18","cited_by_count":236},{"id":"2008.08290","title":"Attribute Prototype Network for Zero-Shot Learning","created":"2020-08-19","cited_by_count":160},{"id":"2203.15102","title":"Rethinking Semantic Segmentation: A Prototype View","created":"2022-03-28","cited_by_count":140},{"id":"1805.03438","title":"Robust Classification with Convolutional Prototype Learning","created":"2018-05-09","cited_by_count":123},{"id":"2403.19651","title":"MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions","created":"2024-03-28","cited_by_count":119},{"id":"1805.00145","title":"Dialog-based Interactive Image Retrieval","created":"2018-05-01","cited_by_count":84},{"id":"2203.08101","title":"ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity","created":"2022-03-15","cited_by_count":83},{"id":"2310.05473","title":"Sentence-level Prompts Benefit Composed Image Retrieval","created":"2023-10-09","cited_by_count":59},{"id":"2308.14746","title":"CoVR-2: Automatic Data Construction for Composed Video Retrieval","created":"2023-08-28","cited_by_count":52},{"id":"2211.07394","title":"Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization","created":"2022-11-14","cited_by_count":45},{"id":"2503.21309","title":"FineCIR: Explicit Parsing of Fine-Grained Modification Semantics for Composed Image Retrieval","created":"2025-03-27","cited_by_count":42},{"id":"2604.17898","title":"ReTrack: Evidence-Driven Dual-Stream Directional Anchor Calibration Network for Composed Video Retrieval","created":"2026-04-20","cited_by_count":41},{"id":"2507.05631","title":"OFFSET: Segmentation-based Focus Shift Revision for Composed Image Retrieval","created":"2025-07-08","cited_by_count":40},{"id":"2303.02483","title":"FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks","created":"2023-03-04","cited_by_count":38},{"id":"2210.06780","title":"Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentation","created":"2022-10-13","cited_by_count":37},{"id":"2309.01366","title":"Target-Guided Composed Image Retrieval","created":"2023-09-04","cited_by_count":36},{"id":"2305.16304","title":"Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encoder","created":"2023-05-25","cited_by_count":35},{"id":"2512.02792","title":"HUD: Hierarchical Uncertainty-Aware Disambiguation Network for Composed Video Retrieval","created":"2025-12-02","cited_by_count":32},{"id":"2204.11212","title":"Progressive Learning for Image Retrieval with Hybrid-Modality Queries","created":"2022-04-24","cited_by_count":26},{"id":"2604.01617","title":"STABLE: Efficient Hybrid Nearest Neighbor Search via Magnitude-Uniformity and Cardinality-Robustness","created":"2026-04-02","cited_by_count":26},{"id":"2604.18051","title":"INTENT: Invariance and Discrimination-aware Noise Mitigation for Robust Composed Image Retrieval","created":"2026-04-20","cited_by_count":26},{"id":"2404.15875","title":"Simple but Effective Raw-Data Level Multimodal Fusion for Composed Image Retrieval","created":"2024-04-24","cited_by_count":24},{"id":"2604.18037","title":"HABIT: Chrono-Synergia Robust Progressive Learning Framework for Composed Image Retrieval","created":"2026-04-20","cited_by_count":24},{"id":"2305.09979","title":"Self-Training Boosted Multi-Factor Matching Network for Composed Image Retrieval","created":"2023-05-17","cited_by_count":22},{"id":"2506.02544","title":"CoRe-MMRAG: Cross-Source Knowledge Reconciliation for Multimodal RAG","created":"2025-06-03","cited_by_count":18},{"id":"2602.19083","title":"ChordEdit: One-Step Low-Energy Transport for Image Editing","created":"2026-02-22","cited_by_count":18},{"id":"2603.26341","title":"HINT: Composed Image Retrieval with Dual-path Compositional Contextualized Network","created":"2026-03-27","cited_by_count":18},{"id":"2604.19386","title":"Air-Know: Arbiter-Calibrated Knowledge-Internalizing Robust Network for Composed Image Retrieval","created":"2026-04-21","cited_by_count":18},{"id":"2603.29291","title":"MELT: Improve Composed Image Retrieval via the Modification Frequentation-Rarity Balance Network","created":"2026-03-31","cited_by_count":17},{"id":"2604.20358","title":"ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval","created":"2026-04-22","cited_by_count":17},{"id":"2604.21806","title":"TEMA: Anchor the Image, Follow the Text for Multi-Modification Composed Image Retrieval","created":"2026-04-23","cited_by_count":15},{"id":"2306.02092","title":"Collaborative Group: Composed Image Retrieval via Consensus Learning from Noisy Annotations","created":"2023-06-03","cited_by_count":14},{"id":"2301.06844","title":"USER: Unified Semantic Enhancement with Momentum Contrast for Image-Text Retrieval","created":"2023-01-17","cited_by_count":13},{"id":"2601.03331","title":"MMErroR: A Benchmark for Erroneous Reasoning in Vision-Language Models","created":"2026-01-06","cited_by_count":10},{"id":"2404.01156","title":"SyncMask: Synchronized Attentional Masking for Fashion-centric Vision-Language Pretraining","created":"2024-04-01","cited_by_count":9},{"id":"2507.12416","title":"QuRe: Query-Relevant Retrieval through Hard Negative Sampling in Composed Image Retrieval","created":"2025-07-16","cited_by_count":8},{"id":"2605.24496","title":"EgoAction: Egocentric Action Composition with Reliability-Aware Temporal Fusion for the EPIC-KITCHENS Action Detection Challenge at CVPR 2026","created":"2026-05-23","cited_by_count":8},{"id":"2509.18602","title":"Training-Free Multi-Style Fusion Through Reference-Based Adaptive Modulation","created":"2025-09-23","cited_by_count":7},{"id":"2605.24500","title":"EgoAdapt: A Multi-Scene Egocentric Adaptation Method for CVPR 2026 HD-EPIC VQA Challenge","created":"2026-05-23","cited_by_count":7},{"id":"2308.08131","title":"Ranking-aware Uncertainty for Text-guided Image Retrieval","created":"2023-08-16","cited_by_count":5},{"id":"2509.18619","title":"Prompt-Guided Dual Latent Steering for Inversion Problems","created":"2025-09-23","cited_by_count":5},{"id":"2605.24470","title":"TempRet: Temporal Enhancement and Two-Stage Reranking for CVPR 2026 EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge","created":"2026-05-23","cited_by_count":5},{"id":"2605.24481","title":"OmniEgo-R$^2$: A Routed Reasoning Framework for the 1st Cross-Domain EgoCross Challenge at CVPR 2026","created":"2026-05-23","cited_by_count":5},{"id":"2606.01113","title":"R^3: Composed Video Retrieval via Reasoning-Guided Recalling and Re-ranking","created":"2026-05-31","cited_by_count":5},{"id":"2404.18114","title":"Deep Boosting Learning: A Brand-new Cooperative Approach for Image-Text Matching","created":"2024-04-28","cited_by_count":4},{"id":"2410.10669","title":"MLP-SLAM: Multilayer Perceptron-Based Simultaneous Localization and Mapping","created":"2024-10-14","cited_by_count":4},{"id":"2602.22595","title":"Don't let the information slip away","created":"2026-02-26","cited_by_count":2}],"next_cursor":null}