Fusing Pseudo Labels with Weak Supervision for Dynamic Traffic Scenarios
Comments This work was accepted as an extended abstract at the International Conference on Computer Vision (ICCV) 2023 BRAVO Workshop, Paris, France
期刊&会议
ICCV
International Conference on Computer Vision · 会议 · Computer Vision
Introducing Language Guidance in Prompt-based Continual Learning
Comments Accepted at ICCV 2023
MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing
Comments ICCV 2023
Context-VQA: Towards Context-Aware and Purposeful Visual Question Answering
Comments Proceedings of ICCV 2023 Workshop on Closing the Loop Between Vision and Language
TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement
Comments Published at ICCV 2023
Going Beyond Nouns With Vision & Language Models Using Synthetic Data
Comments Accepted to ICCV 2023. Project page: https://synthetic-vic.github.io/
Exploring the Benefits of Visual Prompting in Differential Privacy
Comments Published at ICCV 2023
WDiscOOD: Out-of-Distribution Detection via Whitened Linear Discriminant Analysis
Comments Accepted by ICCV 2023. Code is available at: https://github.com/ivalab/WDiscOOD.git
FineDance: A Fine-grained Choreography Dataset for 3D Full Body Dance Generation
Comments Accepted by ICCV 2023
Efficient Model Personalization in Federated Learning via Client-Specific Prompt Generation
Comments Accepted by ICCV 2023
CLIPTrans: Transferring Visual Knowledge with Pre-trained Models for Multimodal Machine Translation
Comments 15 pages, 9 figures, to be published In Proceedings of International Conference of Computer Vision(ICCV), 2023
Group-Conditional Conformal Prediction via Quantile Regression Calibration for Crop and Weed Classification
Journal ref 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), IEEE/CVF, Oct 2023, Paris, France
Learning to Upsample by Learning to Sample
Comments Accepted by ICCV 2023
Exploring Model Transferability through the Lens of Potential Energy
Comments Accepted by ICCV 2023
Walking Your LiDOG: A Journey Through Multiple Domains for LiDAR Semantic Segmentation
Comments Accepted at ICCV 2023
Sat2Density: Faithful Density Learning from Satellite-Ground Image Pairs
Comments ICCV 2023, project page: https://sat2density.github.io/, code: https://github.com/qianmingduowan/Sat2Density
WALDO: Future Video Synthesis using Object Layer Decomposition and Parametric Flow Prediction
Comments Accepted to ICCV 2023
CLNeRF: Continual Learning Meets NeRF
Comments Accepted to ICCV 2023
Score-Based Diffusion Models as Principled Priors for Inverse Imaging
Comments ICCV 2023
Efficient Discovery and Effective Evaluation of Visual Perceptual Similarity: A Benchmark and Beyond
Comments ICCV 2023
R3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple Cameras
Comments Accepted to ICCV 2023. Project page is available at https://www.vis.xyz/pub/r3d3/
S-TREK: Sequential Translation and Rotation Equivariant Keypoints for local feature extraction
Comments Accepted at ICCV 2023
Referring Image Segmentation Using Text Supervision
Comments ICCV 2023
Graph-based Asynchronous Event Processing for Rapid Object Recognition
Comments Accepted to ICCV 2021. Project Page: https://zju3dv.github.io/slide_gcn/
Multi-Modal Neural Radiance Field for Monocular Dense SLAM with a Light-Weight ToF Sensor
Comments Accepted to ICCV 2023 (Oral). Project Page: https://zju3dv.github.io/tof_slam/
Online Continual Learning on Hierarchical Label Expansion
Comments Accepted to ICCV 2023
HoloFusion: Towards Photo-realistic 3D Generative Modeling
Comments ICCV 2023 conference; project page at: https://holodiffusion.github.io/holofusion
Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP
Comments Final version for 5th Workshop on Closing the Loop Between Vision and Language (CLVL) @ ICCV 2023. 4 pages, 5 figures
Sparse Sampling Transformer with Uncertainty-Driven Ranking for Unified Removal of Raindrops and Rain Streaks
Comments Accepted by ICCV'23
Unaligned 2D to 3D Translation with Conditional Vector-Quantized Code Diffusion using Transformers
Comments Camera-ready version for ICCV 2023
