azuxmioy

Render-In-Between

Official implementation for BMVC 2021 paper Render In-between: Motion Guided Video Synthesis for Action Interpolation

fpvsum

FPVSum : First-Person Video Summarization dataset

DanceReID

Official dataset for the paper "Learning from Dances: Pose-Invariant Re-Identification for Multi-Person Tracking" (ICASSP '20)

azuxmioy.github.io

SMnet

Spatiotemporal Multimodal Network for Dynamic Gesture Recognition

ST-ReIDNet

Official implementation of "Learning from Dances: Pose-Invariant Re-Identification for Multi-Person Tracking" (ICASSP '20)

SuperRoad

Road segmentation through multi-objective ensemble and geometric-aware post-processing

tensorflow-CoViAR

DL_Practice

Deep learning practice for students to play with popular deep learning frameworks.

reid-strong-baseline

Bag of Tricks and A Strong Baseline for Deep Person Re-identification