zjr2000
Master student at SUSTech, ShenZhen, China. My research focuses on Computer Vision, specifically exploring the intersection of vision and language learning.
Southern University of Science and TechnologyShen Zhen
Pinned Repositories
Caption-Anything
Caption-Anything is a versatile tool combining image segmentation, visual captioning, and ChatGPT, generating tailored captions with diverse controls for user preferences. https://huggingface.co/spaces/TencentARC/Caption-Anything https://huggingface.co/spaces/VIPLab/Caption-Anything
Awesome-Multimodal-Chatbot
Awesome Multimodal Assistant is a curated list of multimodal chatbots/conversational assistants that utilize various modes of interaction, such as text, speech, images, and videos, to provide a seamless and versatile user experience.
Context-GEBC
Second-place solution to Generic Event Boundary Captioning task in LOVEU Challenge (CVPR 2022 workshop)
easyexcel
快速、简单避免OOM的java处理Excel工具
GVL
Official implementation for paper Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos
LLMVA-GEBC
Winner solution to Generic Event Boundary Captioning task in LOVEU Challenge (CVPR 2023 workshop)
projects
REVERIE
[ECCV2024] Reflective Instruction Tuning: Mitigating Hallucinations in Large Vision-Language Models
Untrimmed-Video-Feature-Extractor
A simple and effective feature extractor for untrimmed videos
zjr2000
zjr2000's Repositories
zjr2000/Awesome-Multimodal-Chatbot
Awesome Multimodal Assistant is a curated list of multimodal chatbots/conversational assistants that utilize various modes of interaction, such as text, speech, images, and videos, to provide a seamless and versatile user experience.
zjr2000/LLMVA-GEBC
Winner solution to Generic Event Boundary Captioning task in LOVEU Challenge (CVPR 2023 workshop)
zjr2000/GVL
Official implementation for paper Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos
zjr2000/REVERIE
[ECCV2024] Reflective Instruction Tuning: Mitigating Hallucinations in Large Vision-Language Models
zjr2000/Untrimmed-Video-Feature-Extractor
A simple and effective feature extractor for untrimmed videos
zjr2000/Context-GEBC
Second-place solution to Generic Event Boundary Captioning task in LOVEU Challenge (CVPR 2022 workshop)
zjr2000/easyexcel
快速、简单避免OOM的java处理Excel工具
zjr2000/projects
zjr2000/zjr2000
zjr2000/zjr2000.github.io