ScaleDet: A Scalable Multi-Dataset Object Detector
Comments CVPR 2023
期刊&会议
CVPR
Conference on Computer Vision and Pattern Recognition · 会议 · Computer Vision
3D Human Keypoints Estimation From Point Clouds in the Wild Without Human Labels
Comments CVPR 2023
ICON$^2$: Reliably Benchmarking Predictive Inequity in Object Detection
Comments Accepted to CVPR 2023 SSAD Workshop
An Overview of Challenges in Egocentric Text-Video Retrieval
Comments 4 pages, CVPR 2023 Joint Ego4D&EPIC Workshop, Extended Abstract
FusedRF: Fusing Multiple Radiance Fields
Comments XRNeRF CVPR Workshop Paper
Q: How to Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!
Comments CVPR 2023
MixPHM: Redundancy-Aware Parameter-Efficient Tuning for Low-Resource Visual Question Answering
Comments 13 pages, 6 figures, 9 tables. Accepted to CVPR 2023
Balanced Product of Calibrated Experts for Long-Tailed Recognition
Comments Accepted at CVPR 2023, 19 pages
Learning Human Mesh Recovery in 3D Scenes
Comments Accepted to CVPR 2023. Project page: https://zju3dv.github.io/sahmr/
Deep Learning-Enabled Sleep Staging From Vital Signs and Activity Measured Using a Near-Infrared Video Camera
Comments Accepted to the 6th International Workshop on Computer Vision for Physiological Measurement (CVPM) at CVPR 2023. 10 pages, 12 figures, 5 tables
Semantic Segmentation on VSPW Dataset through Contrastive Loss and Multi-dataset Training Approach
Comments 1st Place Solution for CVPR 2023 PVUW VSS Track
A Robust Likelihood Model for Novelty Detection
Comments CVPR Workshop on Computer Vision in the Wild, 2023
MoDAR: Using Motion Forecasting for 3D Object Detection in Point Cloud Sequences
Comments CVPR 2023
3rd Place Solution for PVUW2023 VSS Track: A Large Model for Semantic Segmentation on VSPW
Comments 3rd Place Solution for CVPR 2023 PVUW VSS Track
FishEye8K: A Benchmark and Dataset for Fisheye Camera Object Detection
Comments CVPR Workshops 2023
Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspective
Comments Accepted by CVPR 2023 (Highlight)
QuantArt: Quantizing Image Style Transfer Towards High Visual Fidelity
Comments Accepted to CVPR 2023. Code is available at https://github.com/siyuhuang/QuantArt
MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusion
Comments Accepted as a highlight paper in CVPR 2023. Walkthrough video: https://youtu.be/IfGTZwm1abg
Single-Stage 3D Geometry-Preserving Depth Estimation Model Training on Dataset Mixtures with Uncalibrated Stereo Data
Journal ref CVPR 2022
Reassembling Broken Objects using Breaking Curves
Comments 4 pages, accepted at 3DVR Workshop @ CVPR 2023
STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection
Comments 14 pages, 7 figures, accepted by CVPR 2023
Revisiting Class Imbalance for End-to-end Semi-Supervised Object Detection
Comments Accepted at the Efficient Deep Learning for Computer Vision Workshop, CVPR 2023
Transferable Adversarial Attacks on Vision Transformers with Token Gradient Regularization
Comments CVPR 2023, Code is available at https://github.com/jpzhang1810/TGR
Multispectral Contrastive Learning with Viewmaker Networks
Comments Appearing in CVPR-PBVS 2023
Content-aware Token Sharing for Efficient Semantic Segmentation with Vision Transformers
Comments CVPR 2023. Project page and code: https://tue-mps.github.io/CTS/
Self-supervised Interest Point Detection and Description for Fisheye and Perspective Images
Comments CVPR Workshop on Omnidirectional Computer Vision, 2023
Adversarial Attack Based on Prediction-Correction
Comments This manuscript was submitted to CVPR 2022
VILA: Learning Image Aesthetics from User Comments with Vision-Language Pretraining
Comments CVPR 2023, https://github.com/google-research/google-research/tree/master/vila
D3Former: Debiased Dual Distilled Transformer for Incremental Learning
Comments Accepted to CLVision at CVPR 2023
Two-View Geometry Scoring Without Correspondences
Journal ref Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
