leexinhao
I am a MS student at Nanjing University. My research interests mainly lie in efficient video/image understanding and generation methods.
SenseTimeNanjing
Pinned Repositories
leexinhao.github.io
lmms-eval
Accelerating the development of large multimodal models (LMMs) with lmms-eval
mmaction2-next
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
VideoEval
A vision-centric evaluation method for video foundation models that is comprehensive, challenging, indicative, and low-cost.
ZeroI2V
Official implementation of "ZeroI2V: Zero-Cost Adaptation of Pre-trained Transformers from Image to Video" (ECCV2024)
LLaVA-NeXT
VideoEval
VideoEval: Comprehensive Benchmark Suite for Low-Cost Evaluation of Video Foundation Model
ZeroI2V
[ECCV 2024] ZeroI2V: Zero-Cost Adaptation of Pre-trained Transformers from Image to Video
VILA
VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)
InternVideo
[ECCV2024] Video Foundation Models & Data for Multimodal Understanding
leexinhao's Repositories
leexinhao/ZeroI2V
Official implementation of "ZeroI2V: Zero-Cost Adaptation of Pre-trained Transformers from Image to Video" (ECCV2024)
leexinhao/VideoEval
A vision-centric evaluation method for video foundation models that is comprehensive, challenging, indicative, and low-cost.
leexinhao/leexinhao.github.io
leexinhao/lmms-eval
Accelerating the development of large multimodal models (LMMs) with lmms-eval
leexinhao/mmaction2-next
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark