Use of Affective Visual Information for Summarization of Human-Centric Videos

Abstract

Increasing volume of user-generated human-centric video content and their applications, such as video retrieval and browsing, require compact representations that are addressed by the video summarization literature. Current supervised studies formulate video summarization as a sequence-to-sequence learning problem and the existing solutions often neglect the surge of human-centric view, which inherently contains affective content. In this study, we investigate the affective-information enriched supervised video summarization task for human-centric videos. First, we train a visual input-driven state-of-the-art continuous emotion recognition model (CER-NET) on the RECOLA dataset to estimate emotional attributes. Then, we integrate the estimated emotional attributes and the high-level representations from the CER-NET with the visual information to define the proposed affective video summarization architectures (AVSUM). In addition, we investigate the use of attention to improve the AVSUM architectures and propose two new architectures based on temporal attention (TA-AVSUM) and spatial attention (SA-AVSUM). We conduct video summarization experiments on the TvSum database. The proposed AVSUM-GRU architecture with an early fusion of high level GRU embeddings and the temporal attention based TA-AVSUM architecture attain competitive video summarization performances by bringing strong performance improvements for the human-centric videos compared to the state-of-the-art in terms of F-score and self-defined face recall metrics.

A Hierarchical Spatial–Temporal Cross-Attention Scheme for Video Summarization Using Contrastive Learning

“…Ji et al [ 16 ] solve the problem of short-term contextual attention insufficiency and distribution inconsistency. Köprü [ 17 ] proposes two new architectures based on temporal attention (TA-AVSUM) and spatial attention (SA-AVSUM).…”

“…L cro is the loss function of cross-attention. Both L mat and L dat are cross-entropy, as defined by Equation (17). To resolve the centralization issue and reduce the ambiguity problem in key frame filtering, we use L cen for centralization keyframe scores:…”