AutoLabel: CLIP-based framework for Open-set Video Domain Adaptation
Comments Accepted to CVPR 2023
期刊&会议
CVPR
Conference on Computer Vision and Pattern Recognition · 会议 · Computer Vision
Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective
Comments Accepted by CVPR 2023
Detecting Human-Object Contact in Images
Comments Accepted at CVPR 2023
A Probabilistic Framework for Lifelong Test-Time Adaptation
Comments Accepted in CVPR 2023
ALSO: Automotive Lidar Self-supervision by Occupancy estimation
Comments CVPR 2023
Learning to Dub Movies via Hierarchical Prosody Models
Comments accepted to CVPR 2023
A Strong Baseline for Generalized Few-Shot Semantic Segmentation
Comments Accepted to CVPR 2023
MagicPony: Learning Articulated 3D Animals in the Wild
Comments CVPR 2023. Project Page: https://3dmagicpony.github.io/
A Closer Look at Rehearsal-Free Continual Learning
Comments Accepted by the 2023 IEEE/CVF Conference on Computer Vision and Pattern (CVPR) Workshop on Continual Learning in Computer Vision (CLVision 2023)
Neural Volumetric Memory for Visual Locomotion Control
Comments CVPR 2023 Highlight. Our project page with videos is https://rchalyang.github.io/NVM
Burstormer: Burst Image Restoration and Enhancement Transformer
Comments Accepted at CVPR 2023
Use Your Head: Improving Long-Tail Video Recognition
Comments CVPR 2023
DivClust: Controlling Diversity in Deep Clustering
Comments Accepted for publication in CVPR 2023
MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognition
Comments Accepted by CVPR-2023. Code: https://github.com/alibaba-mmai-research/MoLo
Tunable Convolutions with Parametric Multi-Loss Optimization
Comments CVPR 2023
Disorder-invariant Implicit Neural Representation
Comments Journal extension of the CVPR'23 highlight paper "DINER: Disorder-invariant Implicit Neural Representation". In the extension, we model the expressive power of the DINER using parametric functions in the attribute space. As a result, better results are achieved than the conference version. arXiv admin note: substantial text overlap with arXiv:2211.07871
Probabilistic Prompt Learning for Dense Prediction
Comments accepted to CVPR 2023
Learning Anchor Transformations for 3D Garment Animation
Comments Accepted to CVPR 2023. Project page: https://semanticdh.github.io/AnchorDEF
Multi-Modal Representation Learning with Text-Driven Soft Masks
Comments CVPR 2023
How Efficient Are Today's Continual Learning Algorithms?
Comments To appear in the IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPR-W) on Continual Learning in Computer Vision (CLVision) 2023
Zero-shot Referring Image Segmentation with Global-Local Context Features
Comments CVPR 2023
Semi-Weakly Supervised Object Kinematic Motion Prediction
Comments CVPR 2023
SynthVSR: Scaling Up Visual Speech Recognition With Synthetic Supervision
Comments IEEE/CVF CVPR 2023
Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking
Comments CVPR 2023 Camera Ready, 15 pages, 8 figures
Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models
Comments Accepted by CVPR 2023. Project page: https://bluestyle97.github.io/dream3d/
REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory
Comments Published on CVPR 2023
ResFormer: Scaling ViTs with Multi-Resolution Training
Comments CVPR 2023
ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields
Comments CVPR 2023 Highlight. Project page: https://www.idiap.ch/paper/eslam/
BANMo: Building Animatable 3D Neural Models from Many Casual Videos
Comments CVPR 2022 camera-ready version (last update: May 2022)
Enhancing Deformable Local Features by Jointly Learning to Detect and Describe Keypoints
Comments CVPR 2023; Source code available at https://verlab.dcc.ufmg.br/descriptors/dalf_cvpr23
