XiaokunFeng

[ICML'25] CSTrack: Enhancing RGB-X Tracking via Compact Spatiotemporal Features

[NeurIPS'24] MemVLT: Vision-Language Tracking with Adaptive Memory-based Prompts

[ICASSP'25] Enhancing Vision-Language Tracking by Effectively Converting Textual Cues into Visual Cues

[ICCV'25 Highlight] ATCTrack: Aligning Target-Context Cues with Dynamic Target States for Robust Vision-Language Tracking

Accepted by ICML 2026～

No description.

基于演化计算方法的旅行商问题求解，以中国34个城市为例，具体通过遗传进化算法、粒子群优化算法、蚁群优化算法和差分进化算法来实现。

Homepage of Miga

Achieve the iris clssification by Bp network, and the code is realized only by numpy !

Xiaokun Feng's Academic Personal Homepage

No description.

No description.

LLM&VLM Tutorial

[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

CVPR24

A Hierarchical Theme Recognition Model for Sandplay Therapy

A playbook for systematically maximizing the performance of deep learning models.

An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) for key-frame segmentation and Associating Objects with Transformers (AOT) for efficient tracking and propagation purposes.

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

DMControl Generalization Benchmark; RL ;visual based

🏃 Keep updating RL algorithms for MOBA games

DAMO-YOLO: a fast and accurate object detection method with some new techs, including NAS backbones, efficient RepGFPN, ZeroHead, AlignedOTA, and distillation enhancement.

hok game env

Deep Reinforcement Learning for Multiplayer Online Battle Arena

Exercises for the book Artificial Intelligence: A Modern Approach

Machine learning, in numpy

GPT2 for Chinese chitchat/用于中文闲聊的GPT2模型(实现了DialoGPT的MMI思想)

MuLi deep learning course

Config files for my GitHub profile.

High quality, fast, modular reference implementation of SSD in PyTorch

Awesome Multi-label Image Recognition Paper List

achieve self-play?