Stars
ispgroupucl / DeepSportLab
Forked from openpifpaf/openpifpafOfficial implementation of DeepSportLab (a fork of OpenPifPaf)
[ISBI25] Fine-tuning of foundation models with LoRA for cytology classification
Official repository for the paper 'Conformal Predictions for Human Action Recognition with Vision-Language Models'. This repository provides tools for applying conformal prediction to VLMs, leverag…
The code of my master thesis at UCLouvain. Contains a MViT architecture and some pre-processing functions to generate pre-training datasets from unlabelled EEG data.
ElikoPy is Python library aiming at easing the processing of diffusion imaging for microstructural analysis.
Official repository for "Online Gaussian Test-Time Adaptation of Vision-Language Models."
[CVPR 2025 - Highlight] Official implementation of the paper "Realistic Test-Time Adaptation of Vision-Language Models" (StatA).
This repository contains the code of UtiliziNg tRActography to uncoVEr muLti-fixel microstructure (UNRAVEL).
Package facilitating the tracking of sub-cortical U-Fibers
[NeurIPS 2024 - Spotlight] Transduction for Vision-Language Models (TransCLIP): code for the paper "Boosting Vision-Language Models with Transduction".
[CVPR 2024] Zero-shot method for Vision-Language Models based on a robust formulation of the MeanShift algorithm for Test-time Augmentation (MTA).
An easy way to apply LoRA to CLIP. Implementation of the paper "Low-Rank Few-Shot Adaptation of Vision-Language Models" (CLIP-LoRA) [CVPRW 2024].
An extremely fast Python package and project manager, written in Rust.
RTMPose series (RTMPose, DWPose, RTMO, RTMW) without mmcv, mmpose, mmdet etc.
BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models
[ICASSP 2025] Open-source code for the paper "Enhancing Remote Sensing Vision-Language Models for Zero-Shot Scene Classification"
[IEEE TIP] TOPIC: A Parallel Association Paradigm for Multi-Object Tracking under Complex Motions and Diverse Scenes
[ECCV24] Keypoint Promptable Re-Identification: SOTA ReID method robust to occlusions and multi-person ambiguity
PyTorch code and models for V-JEPA self-supervised learning from video.
An open source command line RatioMaster with an optional WebUI.
Football Match Analysis Using YOLO (You Only Look Once).
Official implementation of 🐫 CAMELTrack: Context-Aware Multi-cue ExpLoitation for Online Multi-Object Tracking 🐫
High-resolution models for human tasks.