CVPR 2023

3,088 papers

Top Research Directions

Research directions most represented by CVPR 2023 papers.

Generalizing from Synthetic Data to the Real World 39
Aligning Global Semantics with Local Spatial Precision 34
Mitigating Error Propagation in Pseudo Labeling 32
Accelerating Neural Scene Representations for Real Time Rendering 23
Mitigating Multi View Inconsistency in Generative 3D Modeling 22
Eliminating Per-Scene Optimization with Feed-Forward 3D Reconstruction 22
Overcoming the Static Scene Assumption 21
Exploiting Temporal Redundancy in Video Neural Networks 21
Material Lighting Disentanglement for 3D Reconstruction 21
Bypassing the Computational Bottleneck of Adversarial Training 21
Resolving Shape Radiance Ambiguity in Sparse View Reconstruction 20
Overcoming the Iterative Inference Latency of Diffusion Models 19
Tri-Plane Feature Representations for 3D Deep Learning 18
Deep Learning on Unstructured 3D Point Clouds 17
Resolving Depth Ambiguity in Monocular 3D Reconstruction 17

Top Authors

AuthorPapers
Yu Qiao23
Ying Shan19
Luc Van Gool15
Yi-Zhe Song14
Yongdong Zhang14
Dacheng Tao13
Zhiwei Xiong13
Hongsheng Li12
Jiajun Wu12
Leonidas Guibas12
Michael J. Black12
Yi Yang12
Jie Zhou11
Otmar Hilliges11
Wanli Ouyang11
Yu-Gang Jiang11
Deva Ramanan10
Fahad Shahbaz Khan10
Han Hu10
Jiaya Jia10

Impactful Papers

Papers from CVPR 2023 that shaped research clusters.

Foundational

Influential

Papers

Title
Procedure-Aware Pretraining for Instructional Video Understanding
ProD: Prompting-to-disentangle Domain Knowledge for Cross-domain Few-shot Image Classification
Progressive Backdoor Erasing via connecting Backdoor and Adversarial Attacks
Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesis
Progressively Optimized Local Radiance Fields for Robust View Synthesis
Progressive Neighbor Consistency Mining for Correspondence Pruning
Progressive Open Space Expansion for Open-Set Model Attribution
Progressive Random Convolutions for Single Domain Generalization
Progressive Semantic-Visual Mutual Adaption for Generalized Zero-Shot Learning
Progressive Spatio-temporal Alignment for Efficient Event-based Motion Estimation
Progressive Transformation Learning for Leveraging Virtual Images in Training
Promoting Semantic Connectivity: Dual Nearest Neighbors Contrastive Learning for Unsupervised Domain Generalization
Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences
PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery
Prompt-Free Diffusion: Taking "Text" Out of Text-to-Image Diffusion Models
Prompt, Generate, Then Cache: Cascade of Foundation Models Makes Strong Few-Shot Learners
Prompt-Guided Zero-Shot Anomaly Action Recognition using Pretrained Deep Skeleton Features
Prompt Highlighter: Interactive Control for Multi-Modal LLMs
Prompting Hard or Hardly Prompting: Prompt Inversion for Text-to-Image Diffusion Models
Prompting Large Language Models with Answer Heuristics for Knowledge-Based Visual Question Answering
Propagate and Calibrate: Real-Time Passive Non-Line-of-Sight Tracking
ProphNet: Efficient Agent-Centric Motion Forecasting with Anchor-Informed Proposals
Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action Localization
ProS: Prompting-to-Simulate Generalized Knowledge for Universal Cross-Domain Retrieval
ProTéGé: Untrimmed Pretraining for Video Temporal Grounding by Video Temporal Grounding
Protocon: Pseudo-Label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-Supervised Learning
Prototype-Based Embedding Network for Scene Graph Generation
Prototypical Residual Networks for Anomaly Detection and Localization
Proximal Splitting Adversarial Attack for Semantic Segmentation
ProxyFormer: Proxy Alignment Assisted Point Cloud Completion with Missing Part Sensitive Transformer
Pruning Parameterization with Bi-level Optimization for Efficient Semantic Segmentation on the Edge
Pseudo-Label Guided Contrastive Learning for Semi-Supervised Medical Image Segmentation
PSVT: End-to-End Multi-person 3D Pose and Shape Estimation with Progressive Video Transformers
PTT: Point-Trajectory Transformer for Efficient Temporal 3D Object Detection
Putting People in Their Place: Affordance-Aware Human Insertion into Scenes
Putting the Object Back into Video Object Segmentation
PVO: Panoptic Visual Odometry
PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformer
PyPose: A Library for Robot Learning with Physics-based Optimization
PyramidFlow: High-Resolution Defect Contrastive Localization Using Pyramid Normalizing Flow
Q-DETR: An Efficient Low-Bit Quantized Detection Transformer
QDFormer: Towards Robust Audiovisual Segmentation in Complex Environments with Quantization-based Semantic Decomposition
Q: How to Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!
Q-Instruct: Improving Low-Level Visual Abilities for Multi-Modality Foundation Models
QPGesture: Quantization-Based and Phase-Guided Motion Matching for Natural Speech-Driven Gesture Generation
Quality-aware Pretrained Models for Blind Image Quality Assessment
QuantArt: Quantizing Image Style Transfer Towards High Visual Fidelity
Quantitative Manipulation of Custom Attributes on 3D-Aware Image Synthesis
Quantum-Inspired Spectral-Spatial Pyramid Network for Hyperspectral Image Classification
Quantum Multi-Model Fitting

« prev Page 45/62 next »