[BMVC2023] This is the official repo for Semi-Supervised Domain Generalization for Object Detection via Language-Guided Feature Alignment (BMVC2023)

Code for the BMVC2023 VUA-Workshop conference paper "End-to-end Amodal Video Instance Segmentation"

Includes FSC-147-D and the code for training and testing the CounTX model from the paper Open-world Text-specified Object Counting.

[BMVC 2023] READMem: Robust Embedding Association for a Diverse Memory in Unconstrained Video Object Segmentation

Code for BMVC'23: "Sparse and Privacy-enhanced Representation for Human Pose Estimation"

[BMVC 2023] Mobile Vision Transformer-based Visual Object Tracking

[BMVC CVG 2023 ] Official code for "STEP CATFormer: Spatial-Temporal Effective Body-Part Cross Attention Transformer for Skeleton-based Action Recognition"

[BMVC 2023] Official repository for LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-training

BMVC 2023: Selective Scene Text Removal

[BMVC2023] Official code for TEMI: Exploring the Limits of Deep Image Clustering using Pretrained Models

The official code repository for paper "Rethinking the Encoding of Satellite Image Time Series".

[BMVC 2023 (Oral)] Official pytorch implementation of the paper: "Unsupervised Hashing with Similarity Distribution Calibration"