Video-adverb retrieval with compositional adverb-action embeddings
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:RZN66UIFrecord.jsonopen to challenge →
read the original abstract
Retrieving adverbs that describe an action in a video poses a crucial step towards fine-grained video understanding. We propose a framework for video-to-adverb retrieval (and vice versa) that aligns video embeddings with their matching compositional adverb-action text embedding in a joint embedding space. The compositional adverb-action text embedding is learned using a residual gating mechanism, along with a novel training objective consisting of triplet losses and a regression target. Our method achieves state-of-the-art performance on five recent benchmarks for video-adverb retrieval. Furthermore, we introduce dataset splits to benchmark video-adverb retrieval for unseen adverb-action compositions on subsets of the MSR-VTT Adverbs and ActivityNet Adverbs datasets. Our proposed framework outperforms all prior works for the generalisation task of retrieving adverbs from videos for unseen adverb-action compositions. Code and dataset splits are available at https://hummelth.github.io/ReGaDa/.
This paper has not been read by Pith yet.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.