{"list":"other","total":100,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2307.05782","title":"Large Language Models","created":"2023-07-11","cited_by_count":780},{"id":"1802.06309","title":"Learning Adversarially Fair and Transferable Representations","created":"2018-02-17","cited_by_count":353},{"id":"2304.01186","title":"Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos","created":"2023-04-03","cited_by_count":314},{"id":"2403.20150","title":"TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods","created":"2024-03-29","cited_by_count":249},{"id":"2307.12493","title":"TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition","created":"2023-07-24","cited_by_count":182},{"id":"2305.10120","title":"Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models","created":"2023-05-17","cited_by_count":177},{"id":"2406.01900","title":"Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation","created":"2024-06-04","cited_by_count":174},{"id":"2401.01686","title":"ODTrack: Online Dense Temporal Token Learning for Visual Tracking","created":"2024-01-03","cited_by_count":129},{"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":"2411.03286","title":"DiT4Edit: Diffusion Transformer for Image Editing","created":"2024-11-05","cited_by_count":101},{"id":"2410.12261","title":"CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency Patching","created":"2024-10-16","cited_by_count":94},{"id":"2305.11003","title":"Weakly-Supervised Concealed Object Segmentation with SAM-based Pseudo Labeling and Multi-scale Feature Grouping","created":"2023-05-18","cited_by_count":92},{"id":"2506.05207","title":"Follow-Your-Motion: Video Motion Transfer via Efficient Spatial-Temporal Decoupled Finetuning","created":"2025-06-05","cited_by_count":81},{"id":"2406.11138","title":"Diffusion Models in Low-Level Vision: A Survey","created":"2024-06-17","cited_by_count":74},{"id":"2311.11638","title":"Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model","created":"2023-11-20","cited_by_count":69},{"id":"2308.14103","title":"Towards Unified Token Learning for Vision-Language Tracking","created":"2023-08-27","cited_by_count":62},{"id":"2312.03047","title":"MagicStick: Controllable Video Editing via Control Handle Transformations","created":"2023-12-05","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":"2506.04590","title":"Follow-Your-Creation: Empowering 4D Creation through Video Inpainting","created":"2025-06-05","cited_by_count":62},{"id":"2502.12119","title":"PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection","created":"2025-02-17","cited_by_count":61},{"id":"2506.18046","title":"TAB: Unified Benchmarking of Time Series Anomaly Detection Methods","created":"2025-06-22","cited_by_count":60},{"id":"2108.06455","title":"PTT: Point-Track-Transformer Module for 3D Single Object Tracking in Point Clouds","created":"2021-08-14","cited_by_count":59},{"id":"2406.08850","title":"COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editing","created":"2024-06-13","cited_by_count":59},{"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":"2502.10721","title":"A Comprehensive Survey of Deep Learning for Multivariate Time Series Forecasting: A Channel Strategy Perspective","created":"2025-02-15","cited_by_count":58},{"id":"2111.09571","title":"Person Re-identification Method Based on Color Attack and Joint Defence","created":"2021-11-18","cited_by_count":56},{"id":"2308.03166","title":"Strategic Preys Make Acute Predators: Enhancing Camouflaged Object Detectors by Generating Camouflaged Objects","created":"2023-08-06","cited_by_count":56},{"id":"2406.07255","title":"Towards Realistic Data Generation for Real-World Super-Resolution","created":"2024-06-11","cited_by_count":56},{"id":"2407.21773","title":"RainMamba: Enhanced Locality Learning with State Space Models for Video Deraining","created":"2024-07-31","cited_by_count":56},{"id":"2505.11250","title":"Rethinking Irregular Time Series Forecasting: A Simple yet Effective Baseline","created":"2025-05-16","cited_by_count":55},{"id":"2110.14921","title":"3D Object Tracking with Transformer","created":"2021-10-28","cited_by_count":49},{"id":"2503.06617","title":"Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling","created":"2025-03-09","cited_by_count":48},{"id":"2401.01724","title":"Lightweight Adaptive Feature De-drifting for Compressed Image Classification","created":"2024-01-03","cited_by_count":46},{"id":"2108.05630","title":"3D-SiamRPN: An End-to-End Learning Method for Real-Time 3D Single Object Tracking Using Raw Point Cloud","created":"2021-08-12","cited_by_count":45},{"id":"2503.10270","title":"EEdit: Rethinking the Spatial and Temporal Redundancy for Efficient Image Editing","created":"2025-03-13","cited_by_count":45},{"id":"2501.18898","title":"GestureLSM: Latent Shortcut based Co-Speech Gesture Generation with Spatial-Temporal Modeling","created":"2025-01-31","cited_by_count":44},{"id":"2203.06667","title":"Towards Visual-Prompt Temporal Answering Grounding in Medical Instructional Video","created":"2022-03-13","cited_by_count":43},{"id":"2101.08533","title":"Eliminate Deviation with Deviation for Data Augmentation and a General Multi-modal Data Learning Method","created":"2021-01-21","cited_by_count":42},{"id":"2409.01055","title":"Follow-Your-Canvas: Higher-Resolution Video Outpainting with Extensive Content Generation","created":"2024-09-02","cited_by_count":42},{"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":"2507.05631","title":"OFFSET: Segmentation-based Focus Shift Revision for Composed Image Retrieval","created":"2025-07-08","cited_by_count":40},{"id":"2302.02367","title":"FastPillars: A Deployment-friendly Pillar-based 3D Detector","created":"2023-02-05","cited_by_count":39},{"id":"2408.14562","title":"A Survey of Camouflaged Object Detection and Beyond","created":"2024-08-26","cited_by_count":37},{"id":"2506.14766","title":"ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM","created":"2025-06-17","cited_by_count":37},{"id":"2307.07829","title":"HQG-Net: Unpaired Medical Image Enhancement with High-Quality Guidance","created":"2023-07-15","cited_by_count":36},{"id":"2503.00877","title":"Patch-wise Structural Loss for Time Series Forecasting","created":"2025-03-02","cited_by_count":35},{"id":"2505.16916","title":"Backdoor Cleaning without External Guidance in MLLM Fine-tuning","created":"2025-05-22","cited_by_count":35},{"id":"2308.03063","title":"M$^3$Net: Multi-view Encoding, Matching, and Fusion for Few-shot Fine-grained Action Recognition","created":"2023-08-06","cited_by_count":34},{"id":"2412.01197","title":"InstantSwap: Fast Customized Concept Swapping across Sharp Shape Differences","created":"2024-12-02","cited_by_count":34},{"id":"2108.01266","title":"More but Correct: Generating Diversified and Entity-revised Medical Response","created":"2021-08-03","cited_by_count":31},{"id":"2412.17603","title":"EasyTime: Time Series Forecasting Made Easy","created":"2024-12-23","cited_by_count":30},{"id":"2401.15865","title":"LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection","created":"2024-01-29","cited_by_count":29},{"id":"2501.16583","title":"Directing Mamba to Complex Textures: An Efficient Texture-Aware State Space Model for Image Restoration","created":"2025-01-27","cited_by_count":28},{"id":"2209.00860","title":"Real-time 3D Single Object Tracking with Transformer","created":"2022-09-02","cited_by_count":27},{"id":"2405.18975","title":"Hierarchical Classification Auxiliary Network for Time Series Forecasting","created":"2024-05-29","cited_by_count":26},{"id":"2409.07179","title":"Phy124: Fast Physics-Driven 4D Content Generation from a Single Image","created":"2024-09-11","cited_by_count":23},{"id":"2504.03151","title":"Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)","created":"2025-04-04","cited_by_count":23},{"id":"2503.08271","title":"LangTime: A Language-Guided Unified Model for Time Series Forecasting with Proximal Policy Optimization","created":"2025-03-11","cited_by_count":22},{"id":"2505.06683","title":"UnfoldIR: Rethinking Deep Unfolding Network in Illumination Degradation Image Restoration","created":"2025-05-10","cited_by_count":22},{"id":"2410.07160","title":"TextToon: Real-Time Text Toonify Head Avatar from Single Video","created":"2024-09-23","cited_by_count":21},{"id":"2311.12919","title":"SPOT! Revisiting Video-Language Models for Event Understanding","created":"2023-11-21","cited_by_count":20},{"id":"2406.00050","title":"An Empirical Analysis on Large Language Models in Debate Evaluation","created":"2024-05-28","cited_by_count":20},{"id":"2410.15997","title":"MultiRC: Joint Learning for Time Series Anomaly Prediction and Detection with Multi-scale Reconstructive Contrast","created":"2024-10-21","cited_by_count":19},{"id":"2410.13338","title":"SSD-TS: Exploring the Potential of Linear State Space Models for Diffusion Models in Time Series Imputation","created":"2024-10-17","cited_by_count":18},{"id":"2501.06250","title":"Generative AI for Cel-Animation: A Survey","created":"2025-01-08","cited_by_count":17},{"id":"2401.09386","title":"Tri$^{2}$-plane: Thinking Head Avatar via Feature Pyramid","created":"2024-01-17","cited_by_count":16},{"id":"2409.02431","title":"Adversarial Learning for Neural PDE Solvers with Sparse Data","created":"2024-09-04","cited_by_count":16},{"id":"2411.04656","title":"ICH-SCNet: Intracerebral Hemorrhage Segmentation and Prognosis Classification Network Using CLIP-guided SAM mechanism","created":"2024-11-07","cited_by_count":16},{"id":"2502.12802","title":"PPGF: Probability Pattern-Guided Time Series Forecasting","created":"2025-02-18","cited_by_count":16},{"id":"2505.00416","title":"ScaleTrack: Scaling and back-tracking Automated GUI Agents","created":"2025-05-01","cited_by_count":16},{"id":"2403.15944","title":"Adaptive Super Resolution For One-Shot Talking-Head Generation","created":"2024-03-23","cited_by_count":15},{"id":"2410.09140","title":"RealEra: Semantic-level Concept Erasure via Neighbor-Concept Mining","created":"2024-10-11","cited_by_count":15},{"id":"2503.07191","title":"All That Glitters Is Not Gold: Key-Secured 3D Secrets within 3D Gaussian Splatting","created":"2025-03-10","cited_by_count":15},{"id":"2409.17977","title":"Cross-Modality Attack Boosted by Gradient-Evolutionary Multiform Optimization","created":"2024-09-26","cited_by_count":12},{"id":"2502.07239","title":"Contextual Gesture: Co-Speech Gesture Video Generation through Context-aware Gesture Representation","created":"2025-02-11","cited_by_count":12},{"id":"2506.23121","title":"CRISP-SAM2: SAM2 with Cross-Modal Interaction and Semantic Prompting for Multi-Organ Segmentation","created":"2025-06-29","cited_by_count":12},{"id":"2507.10293","title":"Show and Polish: Reference-Guided Identity Preservation in Face Video Restoration","created":"2025-07-14","cited_by_count":12},{"id":"2204.04344","title":"Towards Better Chinese-centric Neural Machine Translation for Low-resource Languages","created":"2022-04-09","cited_by_count":11},{"id":"2410.07901","title":"Semi-Supervised Video Desnowing Network via Temporal Decoupling Experts and Distribution-Driven Contrastive Regularization","created":"2024-10-10","cited_by_count":11},{"id":"2505.06566","title":"Dynamic Uncertainty Learning with Noisy Correspondence for Text-Based Person Search","created":"2025-05-10","cited_by_count":11},{"id":"2402.11307","title":"ICHPro: Intracerebral Hemorrhage Prognosis Classification Via Joint-attention Fusion-based 3d Cross-modal Network","created":"2024-02-17","cited_by_count":10},{"id":"2407.05238","title":"P2P: Part-to-Part Motion Cues Guide a Strong Tracking Framework for LiDAR Point Clouds","created":"2024-07-07","cited_by_count":10},{"id":"2412.02734","title":"MVCTrack: Boosting 3D Point Cloud Tracking via Multimodal-Guided Virtual Cues","created":"2024-12-03","cited_by_count":10},{"id":"2503.16948","title":"Follow-Your-Color: Multi-Instance Sketch Colorization","created":"2025-03-21","cited_by_count":10},{"id":"2503.19474","title":"A-MESS: Anchor based Multimodal Embedding with Semantic Synchronization for Multimodal Intent Recognition","created":"2025-03-25","cited_by_count":10},{"id":"2505.00941","title":"FreCT: Frequency-augmented Convolutional Transformer for Robust Time Series Anomaly Detection","created":"2025-05-02","cited_by_count":10},{"id":"2504.14205","title":"Dual-channel Heterophilic Message Passing for Graph Fraud Detection","created":"2025-04-19","cited_by_count":8},{"id":"2505.15197","title":"Intentional Gesture: Deliver Your Intentions with Gestures for Speech","created":"2025-05-21","cited_by_count":8},{"id":"2504.14204","title":"DConAD: A Differencing-based Contrastive Representation Learning Framework for Time Series Anomaly Detection","created":"2025-04-19","cited_by_count":7},{"id":"2505.13489","title":"Contrastive Cross-Course Knowledge Tracing via Concept Graph Guided Knowledge Transfer","created":"2025-05-14","cited_by_count":7},{"id":"2505.23270","title":"Does Machine Unlearning Truly Remove Knowledge?","created":"2025-05-29","cited_by_count":7},{"id":"2506.11127","title":"UITron-Speech: Towards Automated GUI Agents Based on Speech Instructions","created":"2025-06-10","cited_by_count":7},{"id":"2402.00827","title":"GaussianStyle: Gaussian Head Avatar via StyleGAN","created":"2024-02-01","cited_by_count":6},{"id":"2404.09051","title":"Rethinking Iterative Stereo Matching from Diffusion Bridge Model Perspective","created":"2024-04-13","cited_by_count":4},{"id":"2504.16516","title":"Think Hierarchically, Act Dynamically: Hierarchical Multi-modal Fusion and Reasoning for Vision-and-Language Navigation","created":"2025-04-23","cited_by_count":3}],"next_cursor":null}