hkchengrex

CascadePSP

[CVPR 2020] CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement

Cutie

[CVPR 2024 Highlight] Putting the Object Back Into Video Object Segmentation

Grounded-Segment-Anything

Grounded-SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

Mask-Propagation

[CVPR 2021] MiVOS - Mask Propagation module. Reproduced STM (and better) with training code :star2:. Semi-supervised video object segmentation evaluation.

MiVOS

[CVPR 2021] Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion. Semi-supervised VOS as well!

MMAudio

[CVPR 2025] MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis

Scribble-to-Mask

[CVPR 2021] MiVOS - Scribble to Mask module

STCN

[NeurIPS 2021] Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation

Tracking-Anything-with-DEVA

[ICCV 2023] Tracking Anything with Decoupled Video Segmentation

XMem

[ECCV 2022] XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model

hkchengrex/XMem

[ECCV 2022] XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model

hkchengrex/MMAudio

[CVPR 2025] MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis

hkchengrex/Tracking-Anything-with-DEVA

[ICCV 2023] Tracking Anything with Decoupled Video Segmentation

hkchengrex/Cutie

[CVPR 2024 Highlight] Putting the Object Back Into Video Object Segmentation

hkchengrex/CascadePSP

[CVPR 2020] CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement

hkchengrex/STCN

[NeurIPS 2021] Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation

hkchengrex/MiVOS

[CVPR 2021] Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion. Semi-supervised VOS as well!

hkchengrex/Mask-Propagation

[CVPR 2021] MiVOS - Mask Propagation module. Reproduced STM (and better) with training code :star2:. Semi-supervised video object segmentation evaluation.

hkchengrex/Scribble-to-Mask

[CVPR 2021] MiVOS - Scribble to Mask module

hkchengrex/Grounded-Segment-Anything

Grounded-SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

hkchengrex/av-benchmark

Benchmarking for Audio-Text and Audio-Visual Generation; Supports FAD, FD_VGG, FD_PANNs, FD_PaSST, IS_PaSST, IS_PANNs, KL_PaSST, KL_PANNs, LAION-CLAP, MS-CLAP, DeSync

hkchengrex/vos-benchmark

Fast and general video object segmentation evaluation.

hkchengrex/C2OT

[ICCV 2025] The Curse of Conditions: Analyzing and Improving Optimal Transport for Conditional Flow-Based Generation

hkchengrex/davis2016-evaluation

hkchengrex/nitrous-ema

Fast and simple post-hoc EMA (Karras et al., 2023) for PyTorch with minimal `.item()` calls. ~78% lower overhead than ema_pytorch.

hkchengrex/shared-memory-tensor-dataset

This repository provides an example of reading from a single shared memory tensor from multiple processes (e.g., with DDP).

hkchengrex/BlenderVOSRenderer

hkchengrex/STM

Video Object Segmentation using Space-Time Memory Networks

hkchengrex/ema-pytorch

A simple way to keep track of an Exponential Moving Average (EMA) version of your pytorch model

hkchengrex/kinetics_to_frames

Convert kinetics datasets (or other video datasets) to frames. Support resizing and temporal sampling for space efficiency.

hkchengrex/Single-View-Metrology-Step-By-Step

An implementation of Single View Metrology (Criminisi99) with step-by-step guidance in a Jupyter Notebook.

hkchengrex/CLAP

Contrastive Language-Audio Pretraining

hkchengrex/fbrs_interactive_segmentation

[CVPR2020] f-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation https://arxiv.org/abs/2001.10331

hkchengrex/ImageBind

ImageBind One Embedding Space to Bind Them All

hkchengrex/MS-CLAP

Learning audio concepts from natural language supervision

hkchengrex/passt_hear21

Inference code for PaSST, using the HEAR API.

hkchengrex/pythia

A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

hkchengrex/RAFT

hkchengrex/RGMP

Fast Video Object Segmentation by Reference-Guided Mask Propagation

hkchengrex/so

Stackoverflow answers