Abstract
Video-based person re-identification (re-ID) aims at matching the same person across video clips. Efficiently exploiting multi-scale fine-grained features while building the structural interaction among them is pivotal for its success. In this paper, we propose a hybrid framework, Dense Interaction Learning (DenseIL), that takes the principal advantages of both CNN-based and Attention-based architectures to tackle video-based person re-ID difficulties. DenseIL contains a CNN Encoder and a Transformer Decoder. The CNN Encoder is responsible for efficiently extracting discriminative spatial features while the Transformer Decoder is designed to deliberately model spatial-temporal inherent interaction across frames. Different from the vanilla Transformer, we additionally let the Transformer Decoder densely attends to intermediate fine-grained CNN features and that naturally yields multi-scale spatial-temporal feature representation for each video clip. Moreover, we introduce Spatio-TEmporal Positional Embedding (STEP-Emb) into the Transformer Decoder to investigate the positional relation among the spatial-temporal inputs. Our experiments consistently and significantly outperform all the state-of-the-art methods on multiple standard video-based re-ID datasets.
Abstract (translated)
URL
https://arxiv.org/abs/2103.09013
