Pinned Repositories
AdaMixer
[CVPR 2022 Oral] AdaMixer: A Fast-Converging Query-Based Object Detector
CamLiFlow
[CVPR 2022 Oral & TPAMI 2023] Learning Optical Flow and Scene Flow with Bidirectional Camera-LiDAR Fusion
EMA-VFI
[CVPR 2023] Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolatio
MeMOTR
[ICCV 2023] MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking
MixFormer
[CVPR 2022 Oral & TPAMI 2024] MixFormer: End-to-End Tracking with Iterative Mixed Attention
MixFormerV2
[NeurIPS 2023] MixFormerV2: Efficient Fully Transformer Tracking
MOC-Detector
[ECCV 2020] Actions as Moving Points
SparseBEV
[ICCV 2023] SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videos
TDN
[CVPR 2021] TDN: Temporal Difference Networks for Efficient Action Recognition
VideoMAE
[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
Multimedia Computing Group, Nanjing University's Repositories
MCG-NJU/VideoMAE
[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
MCG-NJU/MixFormer
[CVPR 2022 Oral & TPAMI 2024] MixFormer: End-to-End Tracking with Iterative Mixed Attention
MCG-NJU/EMA-VFI
[CVPR 2023] Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolatio
MCG-NJU/SparseBEV
[ICCV 2023] SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videos
MCG-NJU/CamLiFlow
[CVPR 2022 Oral & TPAMI 2023] Learning Optical Flow and Scene Flow with Bidirectional Camera-LiDAR Fusion
MCG-NJU/MeMOTR
[ICCV 2023] MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking
MCG-NJU/MixFormerV2
[NeurIPS 2023] MixFormerV2: Efficient Fully Transformer Tracking
MCG-NJU/SportsMOT
[ICCV 2023] SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes
MCG-NJU/SparseOcc
Fully Sparse 3D Occupancy Prediction & RayIoU Evaluation Metric
MCG-NJU/MultiSports
[ICCV 2021] MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions
MCG-NJU/LinK
[CVPR 2023] LinK: Linear Kernel for LiDAR-based 3D Perception
MCG-NJU/MixSort
[ICCV2023] MixSort: The Customized Tracker in SportsMOT
MCG-NJU/STMixer
[CVPR 2023] STMixer: A One-Stage Sparse Action Detector
MCG-NJU/BasicTAD
BasicTAD: an Astounding RGB-Only Baselinefor Temporal Action Detection
MCG-NJU/MOTIP
Multiple Object Tracking as ID Prediction
MCG-NJU/SGM-VFI
[CVPR 2024] Sparse Global Matching for Video Frame Interpolation with Large Motion
MCG-NJU/PointTAD
[NeurIPS 2022] PointTAD: Multi-Label Temporal Action Detection with Learnable Query Points
MCG-NJU/TemporalPerceiver
[T-PAMI 2023] Temporal Perceiver: A General Architecture for Arbitrary Boundary Detection
MCG-NJU/CoMAE
[AAAI 2023] CoMAE: Single Model Hybrid Pre-training on Small-Scale RGB-D Datasets
MCG-NJU/BIVDiff
[CVPR 2024] BIVDiff: A Training-free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion Models
MCG-NJU/PDPP
[CVPR 2023 Hightlight] PDPP: Projected Diffusion for Procedure Planning in Instructional Videos
MCG-NJU/DEQDet
[ICCV 2023] Deep Equilibrium Object Detection
MCG-NJU/EVAD
[ICCV 2023] Efficient Video Action Detection with Token Dropout and Context Refinement
MCG-NJU/MGMAE
[ICCV 2023] MGMAE: Motion Guided Masking for Video Masked Autoencoding
MCG-NJU/APP-Net
[TIP] APP-Net: Auxiliary-point-based Push and Pull Operations for Efficient Point Cloud Recognition
MCG-NJU/StageInteractor
[ICCV 2023] StageInteractor: Query-based Object Detector with Cross-stage Interaction
MCG-NJU/VLG
VLG: General Video Recognition with Web Textual Knowledge (https://arxiv.org/abs/2212.01638)
MCG-NJU/DGN
[IJCV 2023] Dual Graph Networks for Pose Estimation in Crowded Scenes
MCG-NJU/BFRNet
MCG-NJU/LogN
This repo is an official implementation of our IJCV paper: Logit Normalization for Long-Tail Object Detection, which was published in 08 January 2024.