Multimedia Computing Group, Nanjing University

All

67 repositories

FlowDCN
Public
[NeurIPS 2024] Exploring DCN-like Architectures for Fast Image Generation with Arbitrary Resolution
Python
•0•17•0•0•Updated Dec 11, 2024Dec 11, 2024
p-MoD
Public
p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay
Python
•
Apache License 2.0
•2•19•1•0•Updated Dec 10, 2024Dec 10, 2024
MOTIP
Public
Multiple Object Tracking as ID Prediction
tracking computer multi-object-tracking multiple-object-tracking
Python
•
Apache License 2.0
•10•117•6•0•Updated Nov 27, 2024Nov 27, 2024
SPLAM
Public
[ECCV 2024 Oral] SPLAM: Accelerating Image Generation with Sub-path Linear Approximation Model
Python
•
MIT License
•1•19•1•0•Updated Nov 1, 2024Nov 1, 2024
AWT
Public
[NeurIPS 2024] AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation
computer-vision transfer-learning clip video-understanding zero-shot-learning open-set-recognition vlms siglip
Python
•
Apache License 2.0
•2•85•0•0•Updated Oct 5, 2024Oct 5, 2024
VFIMamba
Public
[NeurIPS 2024] VFIMamba: Video Frame Interpolation with State Space Models
Python
•
Apache License 2.0
•7•69•3•0•Updated Sep 26, 2024Sep 26, 2024
Dynamic-MDETR
Public
[TPAMI 2024] Dynamic MDETR: A Dynamic Multimodal Transformer Decoder for Visual Grounding
Python
•
Apache License 2.0
•0•23•0•0•Updated Sep 11, 2024Sep 11, 2024
PRVG
Public
[CVIU 2024] End-to-end dense video grounding via parallel regression
Python
•
Apache License 2.0
•0•6•0•0•Updated Sep 11, 2024Sep 11, 2024
BIVDiff
Public
[CVPR 2024] BIVDiff: A Training-free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion Models
Python
•
Apache License 2.0
•2•63•0•0•Updated Sep 11, 2024Sep 11, 2024
CoMAE
Public
[AAAI 2023 Oral] CoMAE: Single Model Hybrid Pre-training on Small-Scale RGB-D Datasets
rgb-d pre-training aaai2023
Python
•4•34•3•1•Updated Aug 20, 2024Aug 20, 2024
SparseOcc
Public
[ECCV 2024] Fully Sparse 3D Occupancy Prediction & RayIoU Evaluation Metric
Python
•
Apache License 2.0
•23•280•20•1•Updated Aug 15, 2024Aug 15, 2024
ProVP
Public
[IJCV] Progressive Visual Prompt Learning with Contrastive Feature Re-formation
Python
•0•8•0•0•Updated Aug 10, 2024Aug 10, 2024
CamLiFlow
Public
[CVPR 2022 Oral & TPAMI 2023] Learning Optical Flow and Scene Flow with Bidirectional Camera-LiDAR Fusion
point-cloud optical-flow multimodal scene-flow cvpr2022
Python
•23•229•1•0•Updated Jul 29, 2024Jul 29, 2024
ZeroI2V
Public
[ECCV 2024] ZeroI2V: Zero-Cost Adaptation of Pre-trained Transformers from Image to Video
Python
•
Apache License 2.0
•0•16•0•0•Updated Jul 29, 2024Jul 29, 2024
LinK
Public
[CVPR 2023] LinK: Linear Kernel for LiDAR-based 3D Perception
detection point-cloud segmentation autonomous-driving large-kernels nuscenes semantickitti
Python
•
MIT License
•5•88•3•0•Updated Jul 27, 2024Jul 27, 2024
VideoEval
Public
VideoEval: Comprehensive Benchmark Suite for Low-Cost Evaluation of Video Foundation Model
Python
•0•6•0•0•Updated Jul 10, 2024Jul 10, 2024
SGM-VFI
Public
[CVPR 2024] Sparse Global Matching for Video Frame Interpolation with Large Motion
Python
•5•67•1•0•Updated Jul 4, 2024Jul 4, 2024
ViT-TAD
Public
[CVPR 2024] Adapting Short-Term Transformers for Action Detection in Untrimmed Videos
Python
•0•8•0•0•Updated Jun 11, 2024Jun 11, 2024
AMD
Public
[CVPR 2024] Asymmetric Masked Distillation for Pre-Training Small Foundation Models
action-recognition video-understanding distillation self-supervised-learning temporal-action-detection foundation-models small-models cvpr2024
Python
•1•14•1•0•Updated Jun 4, 2024Jun 4, 2024
SportsHHI
Public
[CVPR 2024] SportsHHI: A Dataset for Human-Human Interaction Detection in Sports Videos
Python
•2•11•1•0•Updated May 21, 2024May 21, 2024
MeMOTR
Public
[ICCV 2023] MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking
tracking computer-vision deep-learning multi-object-tracking
Python
•
MIT License
•12•161•6•0•Updated May 9, 2024May 9, 2024
MixFormerV2
Public
[NeurIPS 2023] MixFormerV2: Efficient Fully Transformer Tracking
Python
•
MIT License
•19•144•25•0•Updated Apr 20, 2024Apr 20, 2024
LogN
Public
[IJCV 2024] Logit Normalization for Long-Tail Object Detection
Python
•
Apache License 2.0
•0•5•1•0•Updated Apr 14, 2024Apr 14, 2024
SparseBEV
Public
[ICCV 2023] SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videos
transformer autonomous-driving 3d-object-detection bev-perception
Python
•
MIT License
•27•364•16•0•Updated Mar 31, 2024Mar 31, 2024
MixFormer
Public
[CVPR 2022 Oral & TPAMI 2024] MixFormer: End-to-End Tracking with Iterative Mixed Attention
tracking vot cvpr2022
Python
•
MIT License
•73•465•42•0•Updated Feb 28, 2024Feb 28, 2024
VLG
Public
[IJCV] VLG: General Video Recognition with Web Textual Knowledge (https://arxiv.org/abs/2212.01638)
action-recognition few-shot-recognition open-set-recognition long-tailed-recognition video-language
Python
•0•10•0•0•Updated Jan 18, 2024Jan 18, 2024
StageInteractor
Public
[ICCV 2023] StageInteractor: Query-based Object Detector with Cross-stage Interaction
Python
•
Apache License 2.0
•1•9•0•0•Updated Dec 22, 2023Dec 22, 2023
VideoMAE
Public
[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
transformer video-understanding mae video-analysis video-representation-learning self-supervised-learning masked-autoencoder vision-transformer video-transformer neurips-2022
Python
•
Other
•137•1.4k•44•0•Updated Dec 8, 2023Dec 8, 2023
DGN
Public
[IJCV 2023] Dual Graph Networks for Pose Estimation in Crowded Scenes
Python
•1•7•0•0•Updated Dec 5, 2023Dec 5, 2023
PointTAD
Public
[NeurIPS 2022] PointTAD: Multi-Label Temporal Action Detection with Learnable Query Points
video-understanding action-detection temporal-action-detection neurips-2022
Python
•
Apache License 2.0
•1•41•4•0•Updated Nov 24, 2023Nov 24, 2023