zhiqic

Hyperformer

This is the official implementation of our paper "Hypergraph Transformer for Skeleton-based Action Recognition."

IVAC-P2L

IVAC-P^2L: Leveraging Irregular Repetition Priors for Improving Video Action Counting

DCPT

ChartReader

homepage

CMU-2024-Spring-11-775-MultimediaAnalysis

11775-HW1-2024-Spring

WordArt

This work introduces WordArt Designer, a user-driven framework for artistic typography synthesis, relying on Large Language Models (LLM).

CMU-2023-Fall-11-775-MultimediaAnalysis

TrackGPT

Tracking with Human-Intent Reasoning

MotionEditor

MotionEditor is the first diffusion-based model capable of video motion editing.

KeyPosS

[ACM MM 2023] KeyPosS: Plug-and-Play Facial Landmark Detection through GPS-Inspired True-Range Multilateration

DAMO-StreamNet

[IJCAI 2023] DAMO-StreamNet: Optimizing Streaming Perception in Autonomous Driving

GSRFormer

[ACM-MM 2022] GSRFormer: Grounded Situation Recognition Transformer with Alternate Semantic Attention Refinement

Rethinking-Counting

[CVPR 2022] Rethinking Spatial Invariance of Convolutional Networks for Object Counting

AdvancedProfanityFilter

A browser extension to filter profanity from webpages

11775-HW1-2023-Fall

This is the code repo of HW1 for 11775 Fall 2023

RTPCA

PoSynDA

[ACM MM 2023] PoSynDA: Multi-Hypothesis Pose Synthesis Domain Adaptation for Robust 3D Human Pose Estimation

gen-ai-tutorials

Tutorials for CMU's 2023 Generative AI Tutorial Series

ProContEXT

[ICASSP 2023] ProContEXT: Exploring Progressive Context Transformer for Tracking

LongShortNet

[ICASSP 2023] LongShortNet: Exploring Temporal and Semantic Features Fusion in Streaming Perception

Video2ShopExactMatching

[CVPR 2017] Video2Shop: Exact Matching Clothes in Videos to Online Shopping Images

Awesome-Video-Generation

HQTrack

Tracking Anything in High Quality

llm_tutorial

BlockGCN

This is the official implementation of our paper "Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awareness"

ILA

[ICCV 2023] Implicit Temporal Modeling with Learnable Alignment for Video Recognition

awesome-compose

Awesome Docker Compose samples

ChatIE

official repository for ChatIE paper and a tool of IE using ChatGPT. Note: we set a default openai key in the tool, you can tell us if reach limit. The response speed depends on the official openai chatgpt api. ( sometimes, the official is too crowded and the speed/model will be slow/overloaded.)