{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/object-detection-1/papers/59","list_of":"/task/object-detection-1","task":"object-detection","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":59,"pages_in_order":106,"rows_per_page":100,"rows":[5801,5900],"of":10514,"counts":{"archive_papers_tagged":10514,"with_a_code_link":4285,"where_syntology_ran_a_sample":1027,"not_listed_spam_title":0,"listed":10514,"listed_where_code_ran":1027,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":898,"every_run_a_failure_of_syntologys_instrument":129,"listed_with_a_run_with_no_instrument_failure":898,"listed_every_run_a_failure_of_syntologys_instrument":129,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/object-detection-1","prev":"/task/object-detection-1/papers/58","next":"/task/object-detection-1/papers/60","papers":[{"url":null,"slug":"msu-4s-the-michigan-state-university-four","title":"MSU-4S - The Michigan State University Four Seasons Dataset","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-collaborative-perception-via","title":"Multi-agent Collaborative Perception via Motion-aware Robust Communication Network","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-exposure-fusion-for-high-dynamic-range","title":"Neural Exposure Fusion for High-Dynamic Range Object Detection","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-scaling-up-a-multilingual-vision-and","title":"On Scaling Up a Multilingual Vision and Language Model","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reg-ptq-regression-specialized-post-training","title":"Reg-PTQ: Regression-specialized Post-training Quantization for Fully Quantized Object Detector","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"relational-matching-for-weakly-semi","title":"Relational Matching for Weakly Semi-Supervised Oriented Object Detection","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"scene-adaptive-and-region-aware-multi-modal","title":"Scene-adaptive and Region-aware Multi-modal Prompt for Open Vocabulary Object Detection","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"snida-unlocking-few-shot-object-detection","title":"SNIDA: Unlocking Few-Shot Object Detection with Non-linear Semantic Decoupling Augmentation","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-io-2-scaling-autoregressive-1","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision Language Audio and Action","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unleashing-channel-potential-space-frequency","title":"Unleashing Channel Potential: Space-Frequency Selection Convolution for SAR Object Detection","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/weakly-misalignment-free-adaptive-feature","slug":"weakly-misalignment-free-adaptive-feature","title":"Weakly Misalignment-free Adaptive Feature Alignment for UAVs-based Multimodal Object Detection","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"from-text-to-pixels-a-context-aware-semantic","title":"From Text to Pixels: A Context-Aware Semantic Synergy Solution for Infrared and Visible Image Fusion","date":"2023-12-31","arxiv_id":"2401.00421","repositories_listed":0,"syntology":null},{"url":null,"slug":"horizontal-federated-computer-vision","title":"Horizontal Federated Computer Vision","date":"2023-12-31","arxiv_id":"2401.00390","repositories_listed":0,"syntology":null},{"url":null,"slug":"rainsd-rain-style-diversification-module-for","title":"RainSD: Rain Style Diversification Module for Image Synthesis Enhancement using Feature-Level Style Distribution","date":"2023-12-31","arxiv_id":"2401.00460","repositories_listed":0,"syntology":null},{"url":null,"slug":"ssl-ota-unveiling-backdoor-threats-in-self","title":"SSL-OTA: Unveiling Backdoor Threats in Self-Supervised Learning for Object Detection","date":"2023-12-30","arxiv_id":"2401.00137","repositories_listed":0,"syntology":null},{"url":null,"slug":"mvpatch-more-vivid-patch-for-adversarial","title":"MVPatch: More Vivid Patch for Adversarial Camouflaged Attacks on Object Detectors in the Physical World","date":"2023-12-29","arxiv_id":"2312.17431","repositories_listed":0,"syntology":null},{"url":null,"slug":"delr-active-learning-for-detection-with","title":"DeLR: Active Learning for Detection with Decoupled Localization and Recognition Query","date":"2023-12-28","arxiv_id":"2312.16931","repositories_listed":0,"syntology":null},{"url":null,"slug":"doepatch-dynamically-optimized-ensemble-model","title":"DOEPatch: Dynamically Optimized Ensemble Model for Adversarial Patches Generation","date":"2023-12-28","arxiv_id":"2312.16907","repositories_listed":0,"syntology":null},{"url":null,"slug":"evplug-learn-a-plug-and-play-module-for-event","title":"EvPlug: Learn a Plug-and-Play Module for Event and Image Fusion","date":"2023-12-28","arxiv_id":"2312.16933","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-quantum-convolutional-neural-networks","title":"Fast Quantum Convolutional Neural Networks for Low-Complexity Object Detection in Autonomous Driving Applications","date":"2023-12-28","arxiv_id":"2401.01370","repositories_listed":0,"syntology":null},{"url":null,"slug":"sar-net-multi-scale-direction-aware-sar","title":"Multi-scale direction-aware SAR object detection network via global information fusion","date":"2023-12-28","arxiv_id":"2312.16943","repositories_listed":0,"syntology":null},{"url":null,"slug":"grsdet-learning-to-generate-local-reverse","title":"GRSDet: Learning to Generate Local Reverse Samples for Few-shot Object Detection","date":"2023-12-27","arxiv_id":"2312.16571","repositories_listed":0,"syntology":null},{"url":null,"slug":"virtualpainting-addressing-sparsity-with","title":"VirtualPainting: Addressing Sparsity with Virtual Points and Distance-Aware Data Augmentation for 3D Object Detection","date":"2023-12-26","arxiv_id":"2312.16141","repositories_listed":0,"syntology":null},{"url":null,"slug":"biswift-bandwidth-orchestrator-for-multi","title":"BiSwift: Bandwidth Orchestrator for Multi-Stream Video Analytics on Edge","date":"2023-12-25","arxiv_id":"2312.15740","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-3d-object-detection-using-lidar","title":"End-to-End 3D Object Detection using LiDAR Point Cloud","date":"2023-12-24","arxiv_id":"2312.15377","repositories_listed":0,"syntology":null},{"url":null,"slug":"idet3d-towards-efficient-interactive-object","title":"iDet3D: Towards Efficient Interactive Object Detection for LiDAR Point Clouds","date":"2023-12-24","arxiv_id":"2312.15449","repositories_listed":0,"syntology":null},{"url":null,"slug":"pre-trained-trojan-attacks-for-visual","title":"Pre-trained Trojan Attacks for Visual Recognition","date":"2023-12-23","arxiv_id":"2312.15172","repositories_listed":0,"syntology":null},{"url":null,"slug":"scale-optimization-using-evolutionary","title":"Scale Optimization Using Evolutionary Reinforcement Learning for Object Detection on Drone Imagery","date":"2023-12-23","arxiv_id":"2312.15219","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-enhanced-transformer-for-single-image","title":"Context Enhanced Transformer for Single Image Object Detection","date":"2023-12-22","arxiv_id":"2312.14492","repositories_listed":0,"syntology":null},{"url":null,"slug":"explainable-multi-camera-3d-object-detection","title":"Explainable Multi-Camera 3D Object Detection with Transformer-Based Saliency Maps","date":"2023-12-22","arxiv_id":"2312.14606","repositories_listed":0,"syntology":null},{"url":null,"slug":"fm-ov3d-foundation-model-based-cross-modal","title":"FM-OV3D: Foundation Model-based Cross-modal Knowledge Blending for Open-Vocabulary 3D Detection","date":"2023-12-22","arxiv_id":"2312.14465","repositories_listed":0,"syntology":null},{"url":null,"slug":"fred-towards-a-full-rotation-equivariance-in","title":"FRED: Towards a Full Rotation-Equivariance in Aerial Image Object Detection","date":"2023-12-22","arxiv_id":"2401.06159","repositories_listed":0,"syntology":null},{"url":null,"slug":"lift-attend-splat-bird-s-eye-view-camera","title":"Lift-Attend-Splat: Bird's-eye-view camera-lidar fusion using transformers","date":"2023-12-22","arxiv_id":"2312.14919","repositories_listed":0,"syntology":null},{"url":null,"slug":"meaod-model-extraction-attack-against-object","title":"MEAOD: Model Extraction Attack against Object Detectors","date":"2023-12-22","arxiv_id":"2312.14677","repositories_listed":0,"syntology":null},{"url":null,"slug":"timepillars-temporally-recurrent-3d-lidar","title":"TimePillars: Temporally-Recurrent 3D LiDAR Object Detection","date":"2023-12-22","arxiv_id":"2312.17260","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-power-event-based-face-detection-with","title":"Low-power event-based face detection with asynchronous neuromorphic hardware","date":"2023-12-21","arxiv_id":"2312.14261","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-similarity-perceived-label-assignment","title":"Domain Similarity-Perceived Label Assignment for Domain Generalized Underwater Object Detection","date":"2023-12-20","arxiv_id":"2401.05401","repositories_listed":0,"syntology":null},{"url":null,"slug":"integration-and-performance-analysis-of","title":"Integration and Performance Analysis of Artificial Intelligence and Computer Vision Based on Deep Learning Algorithms","date":"2023-12-20","arxiv_id":"2312.12872","repositories_listed":0,"syntology":null},{"url":null,"slug":"pointenet-a-lightweight-framework-for","title":"PointeNet: A Lightweight Framework for Effective and Efficient Point Cloud Analysis","date":"2023-12-20","arxiv_id":"2312.12743","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffusing-more-objects-for-semi-supervised","title":"Diffusing More Objects for Semi-Supervised Domain Adaptation with Less Labeling","date":"2023-12-19","arxiv_id":"2312.12000","repositories_listed":0,"syntology":null},{"url":null,"slug":"first-qualitative-observations-on-deep","title":"First qualitative observations on deep learning vision model YOLO and DETR for automated driving in Austria","date":"2023-12-19","arxiv_id":"2312.12314","repositories_listed":0,"syntology":null},{"url":null,"slug":"lasa-instance-reconstruction-from-real-scans","title":"LASA: Instance Reconstruction from Real Scans using A Large-scale Aligned Shape Annotation Dataset","date":"2023-12-19","arxiv_id":"2312.12418","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-detection-for-automated-coronary","title":"Object Detection for Automated Coronary Artery Using Deep Learning","date":"2023-12-19","arxiv_id":"2312.12135","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-network-for-multi-person-tracking","title":"Transformer Network for Multi-Person Tracking and Re-Identification in Unconstrained Environment","date":"2023-12-19","arxiv_id":"2312.11929","repositories_listed":0,"syntology":null},{"url":null,"slug":"uniondet-union-level-detector-towards-real-1","title":"UnionDet: Union-Level Detector Towards Real-Time Human-Object Interaction Detection","date":"2023-12-19","arxiv_id":"2312.12664","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-segmentation-of-colonoscopy","title":"Unsupervised Segmentation of Colonoscopy Images","date":"2023-12-19","arxiv_id":"2312.12599","repositories_listed":0,"syntology":null},{"url":null,"slug":"unveiling-spaces-architecturally-meaningful","title":"Unveiling Spaces: Architecturally meaningful semantic descriptions from images of interior spaces","date":"2023-12-19","arxiv_id":"2312.12481","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-based-automatic-groceries-tracking","title":"Vision-Based Automatic Groceries Tracking System -- Smart Homes","date":"2023-12-19","arxiv_id":"2312.12486","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-open-vocabulary-object","title":"Weakly Supervised Open-Vocabulary Object Detection","date":"2023-12-19","arxiv_id":"2312.12437","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffusion-based-particle-detr-for-bev","title":"Diffusion-Based Particle-DETR for BEV Perception","date":"2023-12-18","arxiv_id":"2312.11578","repositories_listed":0,"syntology":null},{"url":null,"slug":"global-feature-pyramid-network","title":"Global Feature Pyramid Network","date":"2023-12-18","arxiv_id":"2312.11231","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-assisted-3d-scene-understanding","title":"Language-Assisted 3D Scene Understanding","date":"2023-12-18","arxiv_id":"2312.11451","repositories_listed":0,"syntology":null},{"url":null,"slug":"liquid-leak-detection-using-thermal-images","title":"Liquid Leak Detection Using Thermal Images","date":"2023-12-18","arxiv_id":"2312.10980","repositories_listed":0,"syntology":null},{"url":null,"slug":"matchdet-a-collaborative-framework-for-image","title":"MatchDet: A Collaborative Framework for Image Matching and Object Detection","date":"2023-12-18","arxiv_id":"2312.10983","repositories_listed":0,"syntology":null},{"url":null,"slug":"satellite-captioning-large-language-models-to","title":"Satellite Captioning: Large Language Models to Augment Labeling","date":"2023-12-18","arxiv_id":"2312.10905","repositories_listed":0,"syntology":null},{"url":null,"slug":"squeezed-edge-yolo-onboard-object-detection","title":"Squeezed Edge YOLO: Onboard Object Detection on Edge Devices","date":"2023-12-18","arxiv_id":"2312.11716","repositories_listed":0,"syntology":null},{"url":null,"slug":"3daxiesprompts-unleashing-the-3d-spatial-task","title":"3DAxiesPrompts: Unleashing the 3D Spatial Task Capabilities of GPT-4V","date":"2023-12-15","arxiv_id":"2312.09738","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-active-perception-for-object-detection","title":"Deep Active Perception for Object Detection using Navigation Proposals","date":"2023-12-15","arxiv_id":"2312.10200","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-training-of-neural-networks-for","title":"End-to-End Training of Neural Networks for Automotive Radar Interference Mitigation","date":"2023-12-15","arxiv_id":"2312.09790","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-uncertainty-aggregation-and","title":"Hierarchical Uncertainty Aggregation and Emphasis Loss for Active Learning in Object Detection","date":"2023-12-15","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-aware-transformation-invariant-roi","title":"Semantic-Aware Transformation-Invariant RoI Align","date":"2023-12-15","arxiv_id":"2312.09609","repositories_listed":0,"syntology":null},{"url":null,"slug":"slowtrack-increasing-the-latency-of-camera","title":"SlowTrack: Increasing the Latency of Camera-based Perception in Autonomous Driving Using Adversarial Examples","date":"2023-12-15","arxiv_id":"2312.09520","repositories_listed":0,"syntology":null},{"url":null,"slug":"ada-yolo-dynamic-fusion-of-yolov8-and","title":"ADA-YOLO: Dynamic Fusion of YOLOv8 and Adaptive Heads for Precise Image Detection and Diagnosis","date":"2023-12-14","arxiv_id":"2312.10099","repositories_listed":0,"syntology":null},{"url":null,"slug":"class-wise-buffer-management-for-incremental","title":"Class-Wise Buffer Management for Incremental Object Detection: An Effective Buffer Training Strategy","date":"2023-12-14","arxiv_id":"2312.09139","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploration-of-visual-prompt-in-grounded-pre","title":"Exploration of visual prompt in Grounded pre-trained open-set detection","date":"2023-12-14","arxiv_id":"2312.08839","repositories_listed":0,"syntology":null},{"url":null,"slug":"learned-fusion-3d-object-detection-using","title":"Learned Fusion: 3D Object Detection using Calibration-Free Transformer Feature Fusion","date":"2023-12-14","arxiv_id":"2312.09082","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancements-in-content-based-image-retrieval","title":"Advancements in Content-Based Image Retrieval: A Comprehensive Survey of Relevance Feedback Techniques","date":"2023-12-13","arxiv_id":"2312.10089","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-invitation-to-deep-reinforcement-learning","title":"An Invitation to Deep Reinforcement Learning","date":"2023-12-13","arxiv_id":"2312.08365","repositories_listed":0,"syntology":null},{"url":null,"slug":"challenges-of-yolo-series-for-object","title":"Challenges of YOLO Series for Object Detection in Extremely Heavy Rain: CALRA Simulator based Synthetic Evaluation Dataset","date":"2023-12-13","arxiv_id":"2312.07976","repositories_listed":0,"syntology":null},{"url":null,"slug":"instance-aware-multi-camera-3d-object","title":"Instance-aware Multi-Camera 3D Object Detection with Structural Priors Mining and Self-Boosting Learning","date":"2023-12-13","arxiv_id":"2312.08004","repositories_listed":0,"syntology":null},{"url":null,"slug":"edge-wasserstein-distance-loss-for-oriented","title":"Edge Wasserstein Distance Loss for Oriented Object Detection","date":"2023-12-12","arxiv_id":"2312.07048","repositories_listed":0,"syntology":null},{"url":null,"slug":"ia2u-a-transfer-plugin-with-multi-prior-for","title":"IA2U: A Transfer Plugin with Multi-Prior for In-Air Model to Underwater","date":"2023-12-12","arxiv_id":"2312.06955","repositories_listed":0,"syntology":null},{"url":null,"slug":"lightweight-high-resolution-subject-matting","title":"Lightweight high-resolution Subject Matting in the Real World","date":"2023-12-12","arxiv_id":"2312.07100","repositories_listed":0,"syntology":null},{"url":null,"slug":"opensight-a-simple-open-vocabulary-framework","title":"OpenSight: A Simple Open-Vocabulary Framework for LiDAR-Based Object Detection","date":"2023-12-12","arxiv_id":"2312.08876","repositories_listed":0,"syntology":null},{"url":null,"slug":"teaching-unknown-objects-by-leveraging-human","title":"Teaching Unknown Objects by Leveraging Human Gaze and Augmented Reality in Human-Robot Interaction","date":"2023-12-12","arxiv_id":"2312.07638","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-perspective-distortion-induced","title":"Mitigating Perspective Distortion-induced Shape Ambiguity in Image Crops","date":"2023-12-11","arxiv_id":"2312.06594","repositories_listed":0,"syntology":null},{"url":null,"slug":"simmining-3d-altitude-aware-3d-object","title":"SimMining-3D: Altitude-Aware 3D Object Detection in Complex Mining Environments: A Novel Dataset and ROS-Based Automatic Annotation Pipeline","date":"2023-12-11","arxiv_id":"2312.06113","repositories_listed":0,"syntology":null},{"url":null,"slug":"squeezesam-user-friendly-mobile-interactive","title":"SqueezeSAM: User friendly mobile interactive segmentation","date":"2023-12-11","arxiv_id":"2312.06736","repositories_listed":0,"syntology":null},{"url":null,"slug":"user-friendly-and-adaptable-discriminative-ai","title":"User Friendly and Adaptable Discriminative AI: Using the Lessons from the Success of LLMs and Image Generation Models","date":"2023-12-11","arxiv_id":"2312.06826","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-yolo-models-towards-outdoor","title":"Investigating YOLO Models Towards Outdoor Obstacle Detection For Visually Impaired People","date":"2023-12-10","arxiv_id":"2312.07571","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-world-object-detection-in-the-era-of","title":"Open World Object Detection in the Era of Foundation Models","date":"2023-12-10","arxiv_id":"2312.05745","repositories_listed":0,"syntology":null},{"url":null,"slug":"immature-green-apple-detection-and-sizing-in","title":"Immature Green Apple Detection and Sizing in Commercial Orchards using YOLOv8 and Shape Fitting Techniques","date":"2023-12-08","arxiv_id":"2401.08629","repositories_listed":0,"syntology":null},{"url":"/paper/lyrics-boosting-fine-grained-language-vision","slug":"lyrics-boosting-fine-grained-language-vision","title":"Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects","date":"2023-12-08","arxiv_id":"2312.05278","repositories_listed":0,"syntology":null},{"url":null,"slug":"forcing-generative-models-to-degenerate-ones","title":"Forcing Generative Models to Degenerate Ones: The Power of Data Poisoning Attacks","date":"2023-12-07","arxiv_id":"2312.04748","repositories_listed":0,"syntology":null},{"url":null,"slug":"gen2det-generate-to-detect","title":"Gen2Det: Generate to Detect","date":"2023-12-07","arxiv_id":"2312.04566","repositories_listed":0,"syntology":null},{"url":null,"slug":"multiview-aerial-visual-recognition-mavrec","title":"Multiview Aerial Visual Recognition (MAVREC): Can Multi-view Improve Aerial Visual Perception?","date":"2023-12-07","arxiv_id":"2312.04548","repositories_listed":0,"syntology":null},{"url":null,"slug":"stable-diffusion-for-data-augmentation-in","title":"Stable Diffusion for Data Augmentation in COCO and Weed Datasets","date":"2023-12-07","arxiv_id":"2312.03996","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-multimodal-data-annotation-via","title":"Automated Multimodal Data Annotation via Calibration With Indoor Positioning System","date":"2023-12-06","arxiv_id":"2312.03608","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-potential-of-vision-language-models-for","title":"The Potential of Vision-Language Models for Content Moderation of Children's Videos","date":"2023-12-06","arxiv_id":"2312.03936","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-holistically-detect-bridges-from","title":"Learning to Holistically Detect Bridges from Large-Size VHR Remote Sensing Imagery","date":"2023-12-05","arxiv_id":"2312.02481","repositories_listed":0,"syntology":null},{"url":null,"slug":"rotatr-detection-transformer-for-dense-and","title":"RotaTR: Detection Transformer for Dense and Rotated Object","date":"2023-12-05","arxiv_id":"2312.02821","repositories_listed":0,"syntology":null},{"url":null,"slug":"uni3dl-unified-model-for-3d-and-language","title":"Uni3DL: Unified Model for 3D and Language Understanding","date":"2023-12-05","arxiv_id":"2312.03026","repositories_listed":0,"syntology":null},{"url":null,"slug":"improv-inpainting-based-multimodal-prompting","title":"IMProv: Inpainting-based Multimodal Prompting for Computer Vision Tasks","date":"2023-12-04","arxiv_id":"2312.01771","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-pseudo-labeler-beyond-noun-concepts","title":"Learning Pseudo-Labeler beyond Noun Concepts for Open-Vocabulary Object Detection","date":"2023-12-04","arxiv_id":"2312.02103","repositories_listed":0,"syntology":null},{"url":null,"slug":"survey-on-deep-learning-in-multimodal-medical","title":"Survey on deep learning in multimodal medical imaging for cancer detection","date":"2023-12-04","arxiv_id":"2312.01573","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-review-and-a-robust-framework-of-data","title":"A Review and A Robust Framework of Data-Efficient 3D Scene Parsing with Traditional/Learned 3D Descriptors","date":"2023-12-03","arxiv_id":"2312.01262","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-adversarial-robustness-of-lidar","title":"Exploring Adversarial Robustness of LiDAR-Camera Fusion Model in Autonomous Driving","date":"2023-12-03","arxiv_id":"2312.01468","repositories_listed":0,"syntology":null},{"url":null,"slug":"scheme-scalable-channer-mixer-for-vision","title":"SCHEME: Scalable Channel Mixer for Vision Transformers","date":"2023-12-01","arxiv_id":"2312.00412","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-efficient-3d-object-detection-in-bird","title":"Towards Efficient 3D Object Detection in Bird's-Eye-View Space for Autonomous Driving: A Convolutional-Only Approach","date":"2023-12-01","arxiv_id":"2312.00633","repositories_listed":0,"syntology":null},{"url":null,"slug":"cascaded-interaction-with-eroded-deep","title":"Cascaded Interaction with Eroded Deep Supervision for Salient Object Detection","date":"2023-11-30","arxiv_id":"2311.18675","repositories_listed":0,"syntology":null}],"record_sha256":"199f6785e2696f9dab53f3427f514d666ea029c44a4dc12ee50ff6fb4a0ac746","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}