Spatial Self-Distillation for Object Detection with Inaccurate Bounding Boxes
Comments accepted by ICCV 2023
期刊&会议
ICCV
International Conference on Computer Vision · 会议 · Computer Vision
Cross-Ray Neural Radiance Fields for Novel-view Synthesis from Unconstrained Image Collections
Comments ICCV 2023 Oral
OmniLabel: A Challenging Benchmark for Language-Based Object Detection
Comments ICCV 2023 Oral - Visit our project website at https://www.omnilabel.org
Implicit Temporal Modeling with Learnable Alignment for Video Recognition
Comments ICCV 2023 oral. 14 pages, 7 figures. Code released at https://github.com/Francis-Rings/ILA
Improved Visual Fine-tuning with Natural Language Supervision
Comments accepted by ICCV'23
DIME-FM: DIstilling Multimodal and Efficient Foundation Models
Comments Accepted to ICCV 2023
Towards Nonlinear-Motion-Aware and Occlusion-Robust Rolling Shutter Correction
Comments accepted at ICCV 2023
Efficient Computation Sharing for Multi-Task Visual Scene Understanding
Comments Camera-Ready version. Accepted to ICCV 2023
Manipulate by Seeing: Creating Manipulation Controllers from Pre-Trained Representations
Comments Oral Presentation at the International Conference on Computer Vision (ICCV), 2023
GPGait: Generalized Pose-based Gait Recognition
Comments ICCV Camera Ready
HaMuCo: Hand Pose Estimation via Multiview Collaborative Self-Supervised Learning
Comments Accepted to ICCV 2023. Won first place in the HANDS22 Challenge Task 2. Project page: https://zxz267.github.io/HaMuCo
MonoNeRF: Learning a Generalizable Dynamic Radiance Field from Monocular Videos
Comments Accepted by ICCV 2023
Minimum Latency Deep Online Video Stabilization
Comments Accepted by ICCV 2023
Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimation
Comments Accepted by ICCV 2023
DELO: Deep Evidential LiDAR Odometry using Partial Optimal Transport
Comments Accepted in ICCV 2023 Workshop
CTP: Towards Vision-Language Continual Pretraining via Compatible Momentum Contrast and Topology Preservation
Comments Accepted by ICCV 2023. Code: https://github.com/KevinLight831/CTP
Masked Motion Predictors are Strong 3D Action Representation Learners
Comments To appear in ICCV 2023
S3IM: Stochastic Structural SIMilarity and Its Unreasonable Effectiveness for Neural Fields
Comments ICCV 2023 main conference. Code: https://github.com/Madaoer/S3IM. 14 pages, 5 figures, 17 tables
Knowing Where to Focus: Event-aware Transformer for Video Grounding
Comments ICCV 2023. Code is available at https://github.com/jinhyunj/EaTR
CBA: Improving Online Continual Learning via Continual Bias Adaptor
Comments Accepted by ICCV 2023
2D3D-MATR: 2D-3D Matching Transformer for Detection-free Registration between Images and Point Clouds
Comments Accepted by ICCV 2023
Towards Deeply Unified Depth-aware Panoptic Segmentation with Bi-directional Guidance Learning
Comments to be published in ICCV 2023
Downstream-agnostic Adversarial Examples
Comments This paper has been accepted by the International Conference on Computer Vision (ICCV '23, October 2--6, 2023, Paris, France)
AlignDet: Aligning Pre-training and Fine-tuning in Object Detection
Comments Camera Ready Version on ICCV 2023. Code and Models are publicly available. Project Page: https://liming-ai.github.io/AlignDet
FlipNeRF: Flipped Reflection Rays for Few-shot Novel View Synthesis
Comments ICCV 2023. Project Page: https://shawn615.github.io/flipnerf/
HumanMAC: Masked Motion Completion for Human Motion Prediction
Comments Accepted by ICCV 2023
FemtoDet: An Object Detection Baseline for Energy Versus Performance Tradeoffs
Comments ICCV 2023
An Embarrassingly Simple Backdoor Attack on Self-supervised Learning
Comments The 2023 International Conference on Computer Vision (ICCV '23)
MotionBERT: A Unified Perspective on Learning Human Motion Representations
Comments ICCV 2023 Camera Ready
Label-Noise Learning with Intrinsically Long-Tailed Data
Comments Accepted by ICCV 2023
