Publications

2025

1. 

   ActAlign: Zero-Shot Fine-Grained Video Classification via Language-Guided Sequence Alignment

   Amir Aghdam and Vincent Tao Hu

   2025

   Abs Bib HTML PDF

   We address the task of zero-shot fine-grained video classification, where no video examples or temporal annotations are available for unseen action classes. While contrastive vision-language models such as SigLIP demonstrate strong open-set recognition via mean-pooled image-text similarity, they fail to capture the temporal structure critical for distinguishing fine-grained activities. We introduce ActAlign, a zero-shot framework that formulates video classification as sequence alignment. For each class, a large language model generates an ordered sub-action sequence, which is aligned with video frames using Dynamic Time Warping (DTW) in a shared embedding space. Without any video-text supervision or fine-tuning, ActAlign achieves 30.5% accuracy on the extremely challenging ActionAtlas benchmark, where human accuracy is only 61.6%. ActAlign outperforms billion-parameter video-language models while using approximately 8x less parameters. These results demonstrate that structured language priors, combined with classical alignment techniques, offer a scalable and general approach to unlocking the open-set recognition potential of vision-language models for fine-grained video understanding.

   @misc{aghdam2025actalignzeroshotfinegrainedvideo,
     title = {ActAlign: Zero-Shot Fine-Grained Video Classification via Language-Guided Sequence Alignment},
     author = {Aghdam, Amir and Hu, Vincent Tao},
     year = {2025},
     eprint = {2506.22967},
     archiveprefix = {arXiv},
     primaryclass = {cs.CV},
   }