Person Re-identification Meets Image Search

Abstract

For long time, person re-identification and image search are two separately studied tasks. However, for person re-identification, the effectiveness of local features and the "query-search" mode make it well posed for image search techniques. In the light of recent advances in image search, this paper proposes to treat person re-identification as an image search problem. Specifically, this paper claims two major contributions. 1) By designing an unsupervised Bag-of-Words representation, we are devoted to bridging the gap between the two tasks by integrating techniques from image search in person re-identification. We show that our system sets up an effective yet efficient baseline that is amenable to further supervised/unsupervised improvements. 2) We contribute a new high quality dataset which uses DPM detector and includes a number of distractor images. Our dataset reaches closer to realistic settings, and new perspectives are provided. Compared with approaches that rely on feature-feature match, our method is faster by over two orders of magnitude. Moreover, on three datasets, we report competitive results compared with the state-of-the-art methods.

References in corpus (1)

• Packing and Padding: Coupled Multi-index for Accurate Image Retrieval

Cited by in corpus (10)

• A Discriminatively Learned CNN Embedding for Person Re-identification
• Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification
• Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification
• Person Search with Natural Language Description
• Orientation Driven Bag of Appearances for Person Re-identification
• The Witt group of real algebraic varieties
• Motion State: A New Benchmark Multiple Object Tracking
• HorNet: A Hierarchical Offshoot Recurrent Network for Improving Person Re-ID via Image Captioning
• Text Guided Person Image Synthesis
• MGD-GAN: Text-to-Pedestrian generation through Multi-Grained Discrimination