From Traditional to Modern : Domain Adaptation for Action Classification in Short Social Video Clips
This work addresses the problem of adapting action classification models from traditional datasets to wild social media videos for researchers and practitioners, but it is incremental in nature.
The paper tackles unsupervised action classification in wild short social video clips by using a domain adaptation strategy that aligns source and target distributions via semantic embeddings and multi-modal hashtag information, achieving notable performance improvements.
Short internet video clips like vines present a significantly wild distribution compared to traditional video datasets. In this paper, we focus on the problem of unsupervised action classification in wild vines using traditional labeled datasets. To this end, we use a data augmentation based simple domain adaptation strategy. We utilise semantic word2vec space as a common subspace to embed video features from both, labeled source domain and unlablled target domain. Our method incrementally augments the labeled source with target samples and iteratively modifies the embedding function to bring the source and target distributions together. Additionally, we utilise a multi-modal representation that incorporates noisy semantic information available in form of hash-tags. We show the effectiveness of this simple adaptation technique on a test set of vines and achieve notable improvements in performance.