Video + CLIP Baseline for Ego4D Long-term Action Anticipation
This work addresses action prediction in egocentric videos, but it is incremental as it adapts existing models without introducing a fundamentally new approach.
The authors tackled long-term action anticipation in videos by combining a pre-trained CLIP model for object understanding with a Slowfast network for temporal modeling, achieving improved performance over the baseline on the Ego4D dataset.
In this report, we introduce our adaptation of image-text models for long-term action anticipation. Our Video + CLIP framework makes use of a large-scale pre-trained paired image-text model: CLIP and a video encoder Slowfast network. The CLIP embedding provides fine-grained understanding of objects relevant for an action whereas the slowfast network is responsible for modeling temporal information within a video clip of few frames. We show that the features obtained from both encoders are complementary to each other, thus outperforming the baseline on Ego4D for the task of long-term action anticipation. Our code is available at github.com/srijandas07/clip_baseline_LTA_Ego4d.