Abstract
Generic Boundary Detection (GBD) aims at locating general boundaries that divide videos into semantically coherent and taxonomy-free units, and could server as an important pre-processing step for long-form video understanding. Previous research separately handle these different-level generic boundaries with specific designs of complicated deep networks from simple CNN to LSTM. Instead, in this paper, our objective is to develop a general yet simple architecture for arbitrary boundary detection in videos. To this end, we present Temporal Perceiver, a general architecture with Transformers, offering a unified solution to the detection of arbitrary generic boundaries. The core design is to introduce a small set of latent feature queries as anchors to compress the redundant input into fixed dimension via cross-attention blocks. Thanks to this fixed number of latent units, it reduces the quadratic complexity of attention operation to a linear form of input frames. Specifically, to leverage the coherence structure of videos, we construct two types of latent feature queries: boundary queries and context queries, which handle the semantic incoherence and coherence regions accordingly. Moreover, to guide the learning of latent feature queries, we propose an alignment loss on cross-attention to explicitly encourage the boundary queries to attend on the top possible boundaries. Finally, we present a sparse detection head on the compressed representations and directly output the final boundary detection results without any post-processing module. We test our Temporal Perceiver on a variety of detection benchmarks, ranging from shot-level, event-level, to scene-level GBD. Our method surpasses the previous state-of-the-art methods on all benchmarks, demonstrating the generalization ability of our temporal perceiver.
Abstract (translated)
URL
https://arxiv.org/abs/2203.00307
