Dense Interaction Learning for Video-based Person Re-identification

TL;DR

This paper introduces Dense Interaction Learning (DenseIL), a hybrid CNN and Attention-based framework that enhances video-based person re-identification by modeling multi-scale spatial-temporal features and interactions.

Contribution

The paper proposes a novel DenseIL framework combining CNN and Attention mechanisms with a Dense Interaction decoder and STEP-Emb for improved re-ID performance.

Findings

Outperforms state-of-the-art on multiple datasets

Effectively models multi-grained spatial-temporal features

Demonstrates significant accuracy improvements

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 Dense Interaction (DI) decoder. The CNN encoder is responsible for efficiently extracting discriminative spatial features while the DI decoder is designed to densely model spatial-temporal inherent interaction across frames. Different from previous works, we additionally let the DI decoder densely attends to intermediate fine-grained CNN features and that naturally yields multi-grained spatial-temporal representation for each video clip. Moreover, we introduce Spatio-TEmporal Positional Embedding (STEP-Emb) into the DI 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 person re-ID datasets.