{"list":"other","total":101,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"1811.00491","title":"A Corpus for Reasoning About Natural Language Grounded in Photographs","created":"2018-11-01","cited_by_count":459},{"id":"2403.06135","title":"MACE: Mass Concept Erasure in Diffusion Models","created":"2024-03-10","cited_by_count":307},{"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":"2307.12493","title":"TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition","created":"2023-07-24","cited_by_count":182},{"id":"2505.17685","title":"FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving","created":"2025-05-23","cited_by_count":166},{"id":"2101.05068","title":"Probabilistic Embeddings for Cross-Modal Retrieval","created":"2021-01-13","cited_by_count":151},{"id":"1809.08545","title":"Bounding Box Regression with Uncertainty for Accurate Object Detection","created":"2018-09-23","cited_by_count":143},{"id":"2401.01686","title":"ODTrack: Online Dense Temporal Token Learning for Visual Tracking","created":"2024-01-03","cited_by_count":129},{"id":"2410.13571","title":"DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation","created":"2024-10-17","cited_by_count":123},{"id":"2410.18775","title":"Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances","created":"2024-10-24","cited_by_count":110},{"id":"2412.20413","title":"EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers","created":"2024-12-29","cited_by_count":95},{"id":"2410.12261","title":"CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency Patching","created":"2024-10-16","cited_by_count":94},{"id":"2411.19548","title":"ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration","created":"2024-11-29","cited_by_count":89},{"id":"2509.22548","title":"JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation","created":"2025-09-26","cited_by_count":89},{"id":"2510.06308","title":"Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding","created":"2025-10-07","cited_by_count":88},{"id":"2412.20367","title":"Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey","created":"2024-12-29","cited_by_count":83},{"id":"2308.14103","title":"Towards Unified Token Learning for Vision-Language Tracking","created":"2023-08-27","cited_by_count":62},{"id":"2312.08733","title":"VMT-Adapter: Parameter-Efficient Transfer Learning for Multi-Task Dense Scene Understanding","created":"2023-12-14","cited_by_count":62},{"id":"2504.12782","title":"Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts","created":"2025-04-17","cited_by_count":62},{"id":"2310.05473","title":"Sentence-level Prompts Benefit Composed Image Retrieval","created":"2023-10-09","cited_by_count":59},{"id":"2111.02036","title":"GRCN: Graph-Refined Convolutional Network for Multimedia Recommendation with Implicit Feedback","created":"2021-11-03","cited_by_count":58},{"id":"2410.11802","title":"TSFM-Bench: A Comprehensive and Unified Benchmark of Foundation Models for Time Series Forecasting","created":"2024-10-15","cited_by_count":58},{"id":"2205.08508","title":"A CLIP-Hitchhiker's Guide to Long Video Retrieval","created":"2022-05-17","cited_by_count":57},{"id":"2301.06309","title":"UATVR: Uncertainty-Adaptive Text-Video Retrieval","created":"2023-01-16","cited_by_count":55},{"id":"2507.02939","title":"Frequency-Aligned Knowledge Distillation for Lightweight Spatiotemporal Forecasting","created":"2025-06-27","cited_by_count":55},{"id":"1810.00319","title":"Modeling Uncertainty with Hedged Instance Embedding","created":"2018-09-30","cited_by_count":52},{"id":"2308.14746","title":"CoVR-2: Automatic Data Construction for Composed Video Retrieval","created":"2023-08-28","cited_by_count":52},{"id":"2505.13408","title":"CoT-Kinetics: A Theoretical Modeling Assessing LRM Reasoning Process","created":"2025-05-19","cited_by_count":51},{"id":"2405.15330","title":"Towards Understanding the Working Mechanism of Text-to-Image Diffusion Model","created":"2024-05-24","cited_by_count":48},{"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":"2503.23512","title":"SCORE: Story Coherence and Retrieval Enhancement for AI Narratives","created":"2025-03-30","cited_by_count":42},{"id":"2306.08832","title":"Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding","created":"2023-06-15","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":"2102.10044","title":"Interest-aware Message-Passing GCN for Recommendation","created":"2021-02-19","cited_by_count":39},{"id":"2404.08928","title":"DeDoDe v2: Analyzing and Improving the DeDoDe Keypoint Detector","created":"2024-04-13","cited_by_count":39},{"id":"2506.14766","title":"ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM","created":"2025-06-17","cited_by_count":37},{"id":"2507.17801","title":"Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modeling","created":"2025-07-23","cited_by_count":37},{"id":"2309.01366","title":"Target-Guided Composed Image Retrieval","created":"2023-09-04","cited_by_count":36},{"id":"2503.18438","title":"ReconDreamer++: Harmonizing Generative and Reconstructive Models for Driving Scene Representation","created":"2025-03-24","cited_by_count":36},{"id":"2505.16916","title":"Backdoor Cleaning without External Guidance in MLLM Fine-tuning","created":"2025-05-22","cited_by_count":35},{"id":"2211.14731","title":"BALF: Simple and Efficient Blur Aware Local Feature Detector","created":"2022-11-27","cited_by_count":34},{"id":"2404.02082","title":"WcDT: World-centric Diffusion Transformer for Traffic Scene Generation","created":"2024-04-02","cited_by_count":32},{"id":"2412.04616","title":"Assessing and Learning Alignment of Unimodal Vision and Language Models","created":"2024-12-05","cited_by_count":32},{"id":"2504.02261","title":"WonderTurbo: Generating Interactive 3D World in 0.72 Seconds","created":"2025-04-03","cited_by_count":32},{"id":"2403.15992","title":"BIMCV-R: A Landmark Dataset for 3D CT Text-Image Retrieval","created":"2024-03-24","cited_by_count":30},{"id":"2507.20177","title":"Towards Universal Modal Tracking with Online Dense Temporal Token Learning","created":"2025-07-27","cited_by_count":30},{"id":"2403.16997","title":"Composed Video Retrieval via Enriched Context and Discriminative Embeddings","created":"2024-03-25","cited_by_count":26},{"id":"2505.19650","title":"Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval","created":"2025-05-26","cited_by_count":26},{"id":"2501.00353","title":"RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions","created":"2024-12-31","cited_by_count":25},{"id":"2507.20016","title":"FedSWA: Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging","created":"2025-07-26","cited_by_count":25},{"id":"2507.21606","title":"Exploring Decoupled Spatio-Temporal Consistency Learning and Self-Prompting Evolution for Self-Supervised Tracking","created":"2025-07-29","cited_by_count":23},{"id":"2305.09979","title":"Self-Training Boosted Multi-Factor Matching Network for Composed Image Retrieval","created":"2023-05-17","cited_by_count":22},{"id":"2407.16658","title":"EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval","created":"2024-07-23","cited_by_count":21},{"id":"2502.13358","title":"Bridging the Editing Gap in LLMs: FineEdit for Precise and Targeted Text Modifications","created":"2025-02-19","cited_by_count":21},{"id":"2310.04148","title":"Self-Supervised Neuron Segmentation with Multi-Agent Reinforcement Learning","created":"2023-10-06","cited_by_count":19},{"id":"2401.06385","title":"SD-MVS: Segmentation-Driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization","created":"2024-01-12","cited_by_count":19},{"id":"2407.11335","title":"LaMI-DETR: Open-Vocabulary Detection with Language Model Instruction","created":"2024-07-16","cited_by_count":19},{"id":"2503.24026","title":"HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation","created":"2025-03-31","cited_by_count":19},{"id":"2509.12446","title":"PromptSculptor: Multi-Agent Based Text-to-Image Prompt Optimization","created":"2025-09-15","cited_by_count":19},{"id":"2503.19296","title":"Fine-grained Textual Inversion Network for Zero-Shot Composed Image Retrieval","created":"2025-03-25","cited_by_count":18},{"id":"2506.02544","title":"CoRe-MMRAG: Cross-Source Knowledge Reconciliation for Multimodal RAG","created":"2025-06-03","cited_by_count":18},{"id":"2508.08438","title":"Selective KV-Cache Sharing to Mitigate Timing Side-Channels in LLM Inference","created":"2025-08-11","cited_by_count":18},{"id":"2505.19694","title":"Knowledge-Aligned Counterfactual-Enhancement Diffusion Perception for Unsupervised Cross-Domain Visual Emotion Recognition","created":"2025-05-26","cited_by_count":17},{"id":"2409.03320","title":"YOLO-PPA based Efficient Traffic Sign Detection for Cruise Control in Autonomous Driving","created":"2024-09-05","cited_by_count":16},{"id":"2503.06456","title":"DynCIM: Dynamic Curriculum for Imbalanced Multimodal Learning","created":"2025-03-09","cited_by_count":16},{"id":"2510.27403","title":"FedMuon: Accelerating Federated Learning with Matrix Orthogonalization","created":"2025-10-31","cited_by_count":16},{"id":"2409.14577","title":"AR Overlay: Training Image Pose Estimation on Curved Surface in a Synthetic Way","created":"2024-09-22","cited_by_count":15},{"id":"2412.19080","title":"Mask Factory: Towards High-quality Synthetic Data Generation for Dichotomous Image Segmentation","created":"2024-12-26","cited_by_count":15},{"id":"2506.12860","title":"QFFT, Question-Free Fine-Tuning for Adaptive Reasoning","created":"2025-06-15","cited_by_count":15},{"id":"2510.27486","title":"FedAdamW: A Communication-Efficient Optimizer with Convergence and Generalization Guarantees for Federated Large Models","created":"2025-10-31","cited_by_count":15},{"id":"2504.03536","title":"HumanDreamer-X: Photorealistic Single-image Human Avatars Reconstruction via Gaussian Restoration","created":"2025-04-04","cited_by_count":13},{"id":"2108.08600","title":"Semantic Compositional Learning for Low-shot Scene Graph Generation","created":"2021-08-19","cited_by_count":12},{"id":"2501.15852","title":"CausalSR: Structural Causal Model-Driven Super-Resolution with Counterfactual Inference","created":"2025-01-27","cited_by_count":12},{"id":"2502.09971","title":"Conditional Latent Coding with Learnable Synthesized Reference for Deep Image Compression","created":"2025-02-14","cited_by_count":11},{"id":"2501.01699","title":"Robust Self-Paced Hashing for Cross-Modal Retrieval with Noisy Labels","created":"2025-01-03","cited_by_count":10},{"id":"2503.04079","title":"Surgical Gaussian Surfels: Highly Accurate Real-time Surgical Scene Rendering using Gaussian Surfels","created":"2025-03-06","cited_by_count":10},{"id":"2509.26614","title":"Hy-Facial: Hybrid Feature Extraction by Dimensionality Reduction Methods for Enhanced Facial Expression Classification","created":"2025-09-30","cited_by_count":10},{"id":"2308.09990","title":"TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo","created":"2023-08-19","cited_by_count":9},{"id":"2505.20124","title":"TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos","created":"2025-05-26","cited_by_count":9},{"id":"2507.13032","title":"Resurrect Mask AutoRegressive Modeling for Efficient and Scalable Image Generation","created":"2025-07-17","cited_by_count":9},{"id":"2510.27504","title":"DP-FedPGN: Finding Global Flat Minima for Differentially Private Federated Learning via Penalizing Gradient Norm","created":"2025-10-31","cited_by_count":9},{"id":"2503.12218","title":"Adaptive Label Correction for Robust Medical Image Segmentation with Noisy Labels","created":"2025-03-15","cited_by_count":8},{"id":"2507.09491","title":"GLIMPSE: Do Large Vision-Language Models Truly Think With Videos or Just Glimpse at Them?","created":"2025-07-13","cited_by_count":8},{"id":"2411.02608","title":"SSFold: Learning to Fold Arbitrary Crumpled Cloth Using Graph Dynamics from Human Demonstration","created":"2024-10-24","cited_by_count":7},{"id":"2501.02414","title":"Journey into Automation: Image-Derived Pavement Texture Extraction and Evaluation","created":"2025-01-05","cited_by_count":7},{"id":"2506.20590","title":"WonderFree: Enhancing Novel View Quality and Cross-View Consistency for 3D Scene Exploration","created":"2025-06-25","cited_by_count":7},{"id":"2511.15015","title":"Dynamic Expert Quantization for Scalable Mixture-of-Experts Inference","created":"2025-11-19","cited_by_count":7},{"id":"2406.10079","title":"Localizing Events in Videos with Multimodal Queries","created":"2024-06-14","cited_by_count":6},{"id":"2505.11335","title":"Understanding and Mitigating Under-Confidence in GNNs from the Final Layer","created":"2025-05-16","cited_by_count":6},{"id":"2507.22872","title":"TR-PTS: Task-Relevant Parameter and Token Selection for Efficient Tuning","created":"2025-07-30","cited_by_count":6},{"id":"2202.13245","title":"Regional-Local Adversarially Learned One-Class Classifier Anomalous Sound Detection in Global Long-Term Space","created":"2022-02-26","cited_by_count":5},{"id":"2408.04914","title":"GuidedNet: Semi-Supervised Multi-Organ Segmentation via Labeled Data Guide Unlabeled Data","created":"2024-08-09","cited_by_count":5},{"id":"2506.22769","title":"Learning Efficient Robotic Garment Manipulation with Standardization","created":"2025-06-28","cited_by_count":5},{"id":"2510.25120","title":"MMM-Fact: A Multimodal, Multi-Domain Fact-Checking Dataset with Multi-Level Retrieval Difficulty","created":"2025-10-29","cited_by_count":5},{"id":"2510.26730","title":"ExpertFlow: Adaptive Expert Scheduling and Memory Coordination for Efficient MoE Inference","created":"2025-10-30","cited_by_count":5},{"id":"2203.01118","title":"A multi-task learning for cavitation detection and cavitation intensity recognition of valve acoustic signals","created":"2022-03-01","cited_by_count":4}],"next_cursor":"100"}