
Sign up to save your podcasts
Or


ArXiv Computer Vision research for Wednesday, June 05, 2024.
00:20: A Self-Supervised Denoising Strategy for Underwater Acoustic Camera Imageries
01:26: Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models
02:40: U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation
04:14: Exploring Data Efficiency in Zero-Shot Learning with Diffusion Models
06:09: P2PFormer: A Primitive-to-polygon Method for Regular Building Contour Extraction from Remote Sensing Images
08:03: Radiomics-guided Multimodal Self-attention Network for Predicting Pathological Complete Response in Breast MRI
09:08: AVFF: Audio-Visual Feature Fusion for Video Deepfake Detection
10:49: Understanding the Impact of Negative Prompts: When and How Do They Take Effect?
12:03: Adversarial Generation of Hierarchical Gaussians for 3D Generative Model
13:45: Event3DGS: Event-based 3D Gaussian Splatting for Fast Egomotion
15:19: DA-Flow: Dual Attention Normalizing Flow for Skeleton-based Video Anomaly Detection
16:56: Sparse Color-Code Net: Real-Time RGB-Based 6D Object Pose Estimation on Edge Devices
18:07: Self-Supervised Skeleton Action Representation Learning: A Benchmark and Beyond
20:01: Enhancing Multimodal Large Language Models with Multi-instance Visual Prompt Generator for Visual Representation Enrichment
21:05: Predicting Genetic Mutation from Whole Slide Images via Biomedical-Linguistic Knowledge Enhanced Multi-label Classification
22:52: A Human-Annotated Video Dataset for Training and Evaluation of 360-Degree Video Summarization Methods
23:53: EdgeSync: Faster Edge-model Updating via Adaptive Continuous Learning for Video Data Drift
25:13: Phy-Diff: Physics-guided Hourglass Diffusion Model for Diffusion MRI Synthesis
26:34: DriVLMe: Enhancing LLM-based Autonomous Driving Agents with Embodied and Social Experiences
27:58: DifAttack++: Query-Efficient Black-Box Adversarial Attack via Hierarchical Disentangled Feature Space in Cross Domain
29:35: Puzzle Pieces Picker: Deciphering Ancient Chinese Characters with Radical Reconstruction
31:02: Instructing Prompt-to-Prompt Generation for Zero-Shot Learning
32:31: Follow-Your-Pose v2: Multiple-Condition Guided Character Image Animation for Stable Pose Control
34:20: Giving each task what it needs -- leveraging structured sparsity for tailored multi-task learning
ArXiv Computer Vision research for Tuesday, June 04, 2024.
00:20: FedDr+: Stabilizing Dot-regression with Global Feature Distillation for Federated Learning
02:06: EUFCC-340K: A Faceted Hierarchical Dataset for Metadata Annotation in GLAM Collections
03:14: Learning to Edit Visual Programs with Self-Supervision
04:15: Low-Rank Adaption on Transformer-based Oriented Object Detector for Satellite Onboard Processing of Remote Sensing Images
06:12: WE-GS: An In-the-wild Efficient 3D Gaussian Representation for Unconstrained Photo Collections
07:39: Decoupling of neural network calibration measures
08:48: IterMask2: Iterative Unsupervised Anomaly Segmentation via Spatial and Frequency Masking for Brain Lesions in MRI
10:29: CoNav: A Benchmark for Human-Centered Collaborative Navigation
12:05: Generative Active Learning for Long-tailed Instance Segmentation
13:17: RoomTex: Texturing Compositional Indoor Scenes via Iterative Inpainting
14:51: Learning Image Priors through Patch-based Diffusion Models for Solving Inverse Problems
16:23: DL-KDD: Dual-Light Knowledge Distillation for Action Recognition in the Dark
18:13: Inpainting Pathology in Lumbar Spine MRI with Latent Diffusion
19:59: Stable-Pose: Leveraging Transformers for Pose-Guided Text-to-Image Generation
21:43: GenS: Generalizable Neural Surface Reconstruction from Multi-View Images
23:20: An Open-Source Tool for Mapping War Destruction at Scale in Ukraine using Sentinel-1 Time Series
24:48: Guiding a Diffusion Model with a Bad Version of Itself
25:59: CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation
27:17: V-Express: Conditional Dropout for Progressive Training of Portrait Video Generation
28:50: DDGS-CT: Direction-Disentangled Gaussian Splatting for Realistic Volume Rendering
30:17: SatSplatYOLO: 3D Gaussian Splatting-based Virtual Object Detection Ensembles for Satellite Feature Recognition
31:24: Enhancing 2D Representation Learning with a 3D Prior
32:32: Parrot: Multilingual Visual Instruction Tuning
34:32: ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
36:20: Enhancing Temporal Consistency in Video Editing by Reconstructing Videos with 3D Gaussian Splatting
38:20: Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning
39:41: Open-YOLO 3D: Towards Fast and Accurate Open-Vocabulary 3D Instance Segmentation
41:52: Dreamguider: Improved Training free Diffusion-based Conditional Generation
43:10: VHS: High-Resolution Iterative Stereo Matching with Visual Hull Priors
ArXiv Computer Vision research for Tuesday, June 04, 2024.
00:20: Plug-and-Play Diffusion Distillation
01:29: Enhance Image-to-Image Generation with LLaVA Prompt and Negative Prompt
02:33: The Crystal Ball Hypothesis in diffusion models: Anticipating object positions from initial noise
04:03: Dealing with All-stage Missing Modality: Towards A Universal Model with Robust Reconstruction and Personalization
05:38: Choroidal Vessel Segmentation on Indocyanine Green Angiography Images via Human-in-the-Loop Labeling
07:31: 3D Imaging of Complex Specular Surfaces by Fusing Polarimetric and Deflectometric Information
08:47: MetaMixer Is All You Need
10:36: Multi-Scale Direction-Aware Network for Infrared Small Target Detection
12:26: Leveraging Predicate and Triplet Learning for Scene Graph Generation
14:15: OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understanding
15:57: FaceCom: Towards High-fidelity 3D Facial Shape Completion via Optimization and Inpainting Guidance
17:17: Domain Game: Disentangle Anatomical Feature for Single Domain Generalized Segmentation
18:41: Analyzing the Effect of Combined Degradations on Face Recognition
19:58: UA-Track: Uncertainty-Aware End-to-End 3D Multi-Object Tracking
21:42: Analyzing the Feature Extractor Networks for Face Image Synthesis
22:59: Radar Spectra-Language Model for Automotive Scene Parsing
24:17: GraVITON: Graph based garment warping with attention guided inversion for Virtual-tryon
25:32: Can CLIP help CLIP in learning 3D?
26:34: Why Only Text: Empowering Vision-and-Language Navigation with Multi-modal Prompts
28:19: SMCL: Saliency Masked Contrastive Learning for Long-tailed Recognition
29:19: I4VGen: Image as Stepping Stone for Text-to-Video Generation
30:34: PuFace: Defending against Facial Cloaking Attacks for Facial Recognition Models
31:57: M3DM-NR: RGB-3D Noisy-Resistant Industrial Anomaly Detection via Multimodal Denoising
33:37: Image contrast enhancement based on the Schr\"odinger operator spectrum
34:44: Understanding Retrieval Robustness for Retrieval-Augmented Image Captioning
35:46: Optimised ProPainter for Video Diminished Reality Inpainting
36:43: Continual Unsupervised Out-of-Distribution Detection
37:55: Progressive Confident Masking Attention Network for Audio-Visual Segmentation
39:06: Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation
ArXiv Computer Vision research for Monday, June 03, 2024.
00:20: Mixture of Rationale: Multi-Modal Reasoning Mixture for Visual Question Answering
01:35: An expert-driven data generation pipeline for histological images
02:26: Sensitivity-Informed Augmentation for Robust Segmentation
04:10: EAGLE: Efficient Adaptive Geometry-based Learning in Cross-view Understanding
05:44: ED-SAM: An Efficient Diffusion Sampling Approach to Domain Generalization in Vision-Language Foundation Models
07:12: SLANT: Spurious Logo ANalysis Toolkit
09:09: SAM as the Guide: Mastering Pseudo-Label Refinement in Semi-Supervised Referring Expression Segmentation
10:48: Automatic Fused Multimodal Deep Learning for Plant Identification
12:19: MLIP: Efficient Multi-Perspective Language-Image Pretraining with Exhaustive Data Utilization
13:53: DreamPhysics: Learning Physical Properties of Dynamic 3D Gaussians with Video Diffusion Priors
15:27: Towards Automating the Retrospective Generation of BIM Models: A Unified Framework for 3D Semantic Reconstruction of the Built Environment
16:07: Differentiable Task Graph Learning: Procedural Activity Representation and Online Mistake Detection from Egocentric Videos
17:42: DA-HFNet: Progressive Fine-Grained Forgery Image Detection and Localization Based on Dual Attention
18:58: Learning Temporally Consistent Video Depth from Video Diffusion Priors
20:42: Robust Classification by Coupling Data Mollification with Label Smoothing
21:27: ELSA: Evaluating Localization of Social Activities in Urban Streets
23:17: Towards Flexible Interactive Reflection Removal with Human Guidance
25:08: Prototypical Transformer as Unified Motion Learners
26:18: Long and Short Guidance in Score identity Distillation for One-Step Text-to-Image Generation
27:52: Tetrahedron Splatting for 3D Generation
29:40: Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP
31:03: SpatialRGPT: Grounded Spatial Reasoning in Vision Language Model
32:44: DeNVeR: Deformable Neural Vessel Representations for Unsupervised Video Vessel Segmentation
33:53: Text-guided Controllable Mesh Refinement for Interactive 3D Modeling
35:01: Reconstructing and Simulating Dynamic 3D Objects with Mesh-adsorbed Gaussian Splatting
36:19: DiffUHaul: A Training-Free Method for Object Dragging in Images
37:58: MultiPly: Reconstruction of Multiple People from Monocular Video in the Wild
ArXiv Computer Vision research for Monday, June 03, 2024.
00:20: Patch-Based Encoder-Decoder Architecture for Automatic Transmitted Light to Fluorescence Imaging Transition: Contribution to the LightMyCells Challenge
01:26: UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation
03:18: S-CycleGAN: Semantic Segmentation Enhanced CT-Ultrasound Image-to-Image Translation for Robotic Ultrasonography
04:26: AFF-ttention! Affordances and Attention models for Short-Term Object Interaction Anticipation
06:04: 3D WholeBody Pose Estimation based on Semantic Graph Attention Network and Distance Information
07:21: Scaling Up Deep Clustering Methods Beyond ImageNet-1K
08:36: GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer
10:11: Augmented Commonsense Knowledge for Remote Object Grounding
11:47: FreeTumor: Advance Tumor Segmentation via Large-Scale Tumor Synthesis
13:44: fruit-SALAD: A Style Aligned Artwork Dataset to reveal similarity perception in image embeddings
15:06: Capsule Enhanced Variational AutoEncoder for Underwater Image Reconstruction
16:51: Enhancing Dynamic CT Image Reconstruction with Neural Fields Through Explicit Motion Regularizers
18:01: pOps: Photo-Inspired Diffusion Operators
19:25: Pulmonary Embolism Mortality Prediction Using Multimodal Learning Based on Computed Tomography Angiography and Clinical Data
21:52: Compute-Efficient Medical Image Classification with Softmax-Free Transformers and Sequence Normalization
23:21: Scale-Free Image Keypoints Using Differentiable Persistent Homology
24:14: Enhancing Inertial Hand based HAR through Joint Representation of Language, Pose and Synthetic IMUs
25:32: TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy
27:29: HHMR: Holistic Hand Mesh Recovery by Enhancing the Multimodal Controllability of Graph Diffusion Models
29:13: ARCH2S: Dataset, Benchmark and Challenges for Learning Exterior Architectural Structures from Point Clouds
30:04: Unleashing Generalization of End-to-End Autonomous Driving with Controllable Long Video Generation
31:46: Differentially Private Fine-Tuning of Diffusion Models
33:40: MP-PolarMask: A Faster and Finer Instance Segmentation for Concave Images
34:57: From Feature Visualization to Visual Circuits: Effect of Adversarial Model Manipulation
36:12: Convolutional Unscented Kalman Filter for Multi-Object Tracking with Outliers
37:41: AutoStudio: Crafting Consistent Subjects in Multi-turn Interactive Image Generation
39:41: TE-NeXt: A LiDAR-Based 3D Sparse Convolutional Network for Traversability Estimation
ArXiv Computer Vision research for Monday, June 03, 2024.
00:20: Dragonfly: Multi-Resolution Zoom Supercharges Large Visual-Language Model
02:26: MultiEdits: Simultaneous Multi-Aspect Editing with Text-to-Image Diffusion Models
03:57: Uni-ISP: Unifying the Learning of ISPs from Multiple Cameras
05:36: CLIP-Guided Attribute Aware Pretraining for Generalizable Image Quality Assessment
07:01: Khayyam Offline Persian Handwriting Dataset
08:04: LLEMamba: Low-Light Enhancement via Relighting-Guided Mamba with Deep Unfolding Network
09:31: CYCLO: Cyclic Graph Transformer Approach to Multi-Object Relationship Modeling in Aerial Videos
11:00: Generalized Jersey Number Recognition Using Multi-task Learning With Orientation-guided Weight Refinement
12:41: Synthetic Data Generation for 3D Myocardium Deformation Analysis
14:00: Self-Calibrating 4D Novel View Synthesis from Monocular Videos Using Gaussian Splatting
15:51: Virtual avatar generation models as world navigators
16:26: VIP: Versatile Image Outpainting Empowered by Multimodal Large Language Model
18:04: SceneTextGen: Layout-Agnostic Scene Text Image Synthesis with Diffusion Models
19:32: DANCE: Dual-View Distribution Alignment for Dataset Condensation
21:10: UniQA: Unified Vision-Language Pre-training for Image Quality and Aesthetic Assessment
22:47: Visual Car Brand Classification by Implementing a Synthetic Image Dataset Creation Pipeline
23:50: Understanding the Cross-Domain Capabilities of Video-Based Few-Shot Action Recognition Models
25:42: Estimating Canopy Height at Scale
26:50: CUT: A Controllable, Universal, and Training-Free Visual Anomaly Generation Framework
27:59: Object Aware Egocentric Online Action Detection
29:06: BACON: Bayesian Optimal Condensation Framework for Dataset Distillation
30:49: $\Delta$-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers
32:29: Learning Adaptive Fusion Bank for Multi-modal Salient Object Detection
34:18: Towards Practical Single-shot Motion Synthesis
35:37: DeepUniUSTransformer: Towards A Universal UltraSound Model with Prompted Guidance
37:12: Dimba: Transformer-Mamba Diffusion Models
38:35: Zero-Shot Out-of-Distribution Detection with Outlier Label Exposure
ArXiv Computer Vision research for Sunday, June 02, 2024.
00:20: Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering
02:12: SAM-LAD: Segment Anything Model Meets Zero-Shot Logic Anomaly Detection
04:12: Correlation Matching Transformation Transformers for UHD Image Restoration
06:06: MGI: Multimodal Contrastive pre-training of Genomic and Medical Imaging
07:23: Diff-Mosaic: Augmenting Realistic Representations in Infrared Small Target Detection via Diffusion Prior
09:19: T2LM: Long-Term 3D Human Motion Generation from Multiple Sentences
11:00: Representing Animatable Avatar via Factorized Neural Fields
12:24: An Information Compensation Framework for Zero-Shot Skeleton-based Action Recognition
14:01: Ultrasound Report Generation with Cross-Modality Feature Alignment via Unsupervised Guidance
15:18: SimSAM: Zero-shot Medical Image Segmentation via Simulated Interaction
16:57: Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation
18:16: Task-oriented Embedding Counts: Heuristic Clustering-driven Feature Fine-tuning for Whole Slide Image Classification
19:49: W-Net: A Facial Feature-Guided Face Super-Resolution Network
21:25: Exploiting Frequency Correlation for Hyperspectral Image Reconstruction
22:46: Deciphering Oracle Bone Language with Diffusion Models
24:07: Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training
25:29: Lay-A-Scene: Personalized 3D Object Arrangement Using Text-to-Image Priors
26:35: Bilinear-Convolutional Neural Network Using a Matrix Similarity-based Joint Loss Function for Skin Disease Classification
27:54: Towards General Robustness Verification of MaxPool-based Convolutional Neural Networks via Tightening Linear Approximation
29:22: An Optimized Toolbox for Advanced Image Processing with Tsetlin Machine Composites
30:47: A Survey of Deep Learning Based Radar and Vision Fusion for 3D Object Detection in Autonomous Driving
32:07: Explore Internal and External Similarity for Single Image Deraining with Graph Neural Networks
33:48: CCF: Cross Correcting Framework for Pedestrian Trajectory Prediction
35:38: Freeplane: Unlocking Free Lunch in Triplane-Based Sparse-View Reconstruction Models
37:09: Once-for-All: Controllable Generative Image Compression with Dynamic Granularity Adaption
38:53: Unsupervised Contrastive Analysis for Salient Pattern Detection using Conditional Diffusion Models
40:42: Diffusion Features to Bridge Domain Gap for Semantic Segmentation
42:26: AI-Face: A Million-Scale Demographically Annotated AI-Generated Face Dataset and Fairness Benchmark
43:46: Towards Point Cloud Compression for Machine Perception: A Simple and Strong Baseline by Learning the Octree Depth Level Predictor
45:19: PruNeRF: Segment-Centric Dataset Pruning via 3D Spatial Consistency
46:36: EchoNet-Synthetic: Privacy-preserving Video Generation for Safe Medical Data Sharing
48:07: Stealing Image-to-Image Translation Models With a Single Query
49:21: Collaborative Novel Object Discovery and Box-Guided Cross-Modal Alignment for Open-Vocabulary 3D Object Detection
51:08: Eating Smart: Advancing Health Informatics with the Grounding DINO based Dietary Assistant App
52:21: DistilDIRE: A Small, Fast, Cheap and Lightweight Diffusion Synthesized Deepfake Detection
53:40: Streaming quanta sensors for online, high-performance imaging and vision
55:14: OLIVE: Object Level In-Context Visual Embeddings
56:31: Visual place recognition for aerial imagery: A survey
57:54: Global High Categorical Resolution Land Cover Mapping via Weak Supervision
59:49: DDA: Dimensionality Driven Augmentation Search
ArXiv Computer Vision research for Saturday, June 01, 2024.
00:20: Complex Style Image Transformations for Domain Generalization in Medical Images
01:36: HENASY: Learning to Assemble Scene-Entities for Egocentric Video-Language Model
03:03: From Seedling to Harvest: The GrowingSoy Dataset for Weed Detection in Soy Crops via Instance Segmentation
04:30: Quality Sentinel: Estimating Label Quality and Errors in Medical Segmentation Datasets
06:22: Whole Heart 3D+T Representation Learning Through Sparse 2D Cardiac MR Images
08:08: Image Captioning via Dynamic Path Customization
09:29: DSCA: A Digital Subtraction Angiography Sequence Dataset and Spatio-Temporal Model for Cerebral Artery Segmentation
11:29: DeCoOp: Robust Prompt Tuning with Out-of-Distribution Detection
12:55: Details Enhancement in Unsigned Distance Field Learning for High-fidelity 3D Surface Reconstruction
14:21: E$^3$-Net: Efficient E(3)-Equivariant Normal Estimation Network
15:30: An Effective Weight Initialization Method for Deep Learning: Application to Satellite Image Classification
16:52: SynthBA: Reliable Brain Age Estimation Across Multiple MRI Sequences and Resolutions
18:40: SpikeMM: Flexi-Magnification of High-Speed Micro-Motions
20:21: CapeX: Category-Agnostic Pose Estimation from Textual Point Explanation
21:51: DS@BioMed at ImageCLEFmedical Caption 2024: Enhanced Attention Mechanisms in Medical Caption Generation through Concept Detection Integration
23:17: Arabic Handwritten Text for Person Biometric Identification: A Deep Learning Approach
24:32: Multimodal Metadata Assignment for Cultural Heritage Artifacts
25:33: You Only Need Less Attention at Each Stage in Vision Transformers
27:02: Towards Generalizable Multi-Object Tracking
28:16: Localize, Understand, Collaborate: Semantic-Aware Dragging via Intention Reasoner
29:45: MoDGS: Dynamic Gaussian Splatting from Causually-captured Monocular Videos
30:52: Topo4D: Topology-Preserving Gaussian Splatting for High-Fidelity 4D Head Capture
32:28: GLCAN: Global-Local Collaborative Auxiliary Network for Local Learning
33:41: DroneVis: Versatile Computer Vision Library for Drones
34:28: Bilateral Guided Radiance Field Processing
36:11: Dual Hyperspectral Mamba for Efficient Spectral Compressive Imaging
37:59: The Curious Case of End Token: A Zero-Shot Disentangled Image Editing using CLIP
38:53: Pedestrian intention prediction in Adverse Weather Conditions with Spiking Neural Networks and Dynamic Vision Sensors
40:28: Adapting Fine-Grained Cross-View Localization to Areas without Fine Ground Truth
41:59: End-to-End Model-based Deep Learning for Dual-Energy Computed Tomography Material Decomposition
43:00: AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning
44:38: Effectiveness of Vision Language Models for Open-world Single Image Test Time Adaptation
45:54: Research on the Application of Computer Vision Based on Deep Learning in Autonomous Driving Technology
47:12: SAM-VMNet: Deep Neural Networks For Coronary Angiography Vessel Segmentation
48:58: Audio-Visual Talker Localization in Video for Spatial Sound Reproduction
50:27: 2nd Place Solution for PVUW Challenge 2024: Video Panoptic Segmentation
51:36: Diffusion-based Image Generation for In-distribution Data Augmentation in Surface Defect Detection
53:22: Improving Text Generation on Images with Synthetic Captions
54:24: FlowIE: Efficient Image Enhancement via Rectified Flow
56:00: Learning Background Prompts to Discover Implicit Knowledge for Open Vocabulary Object Detection
57:29: On the use of first and second derivative approximations for biometric online signature recognition
58:07: Memory-guided Network with Uncertainty-based Feature Augmentation for Few-shot Semantic Segmentation
From the publisher's feed