A Pose-Sensitive Embedding for Person Re-identification with Expanded Cross Neighborhood Re-ranking

By M. Sarfraz, Arne Schumann, Andreas Eberle, Rainer Stiefelhagen. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2017

522 citations recorded by the source corpus.

Person re-identification is a challenging retrieval task that requires matching a person's acquired image across non-overlapping camera views. In this paper we propose an effective approach that incorporates both the fine and coarse pose information of the person to learn a discriminative embedding. In contrast to the recent direction of explicitly modeling body parts or correcting for misalignment based on these, we show that a rather straightforward inclusion of acquired camera view and/or the detected joint locations into a convolutional neural network helps to learn a very effective representation. To increase retrieval performance, re-ranking techniques based on computed distances have recently gained much attention. We propose a new unsupervised and automatic re-ranking framework that achieves state-of-the-art re-ranking performance. We show that in contrast to the current state-of-the-art re-ranking methods our approach does not require to compute new rank lists for each image pair (e.g., based on reciprocal neighbors) and performs well by using simple direct rank list based comparison or even by just using the already computed euclidean distances between the images. We show that both our learned representation and our re-ranking method achieve state-of-the-art performance on a number of challenging surveillance image and video datasets. Code is available at https://github.com/pse-ecn.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/a4958d26a3aaf77081fcb9b76393a30bf722e92e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Deep Learning for Person Re-Identification: A Survey and Outlook (2020, methodology): “Similarly, the camera view information or the detected camera location is also applied in [17] to improve the feature representation with camera-speciﬁc information modeling.”
Pyramidal Person Re-IDentification via Multi-Loss Dynamic Training (2018, background): “Furthermore, both the ﬁne and coarse pose information of the person [19] are incorporated to learn a discriminative embedding.”
Pose-Invariant Embedding for Deep Person Re-Identification (2017, methodology): “In [29], three pose types (front, back, side) are used as the coarse pose constraints, and the raw response maps corresponding to each pose are used as fine pose constraints.”
High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification (2020, methodology): “holistic ReID datasets Market-1501 [42] and DukeMTMCreID [28, 46], and compare with 3 vanilla ReID methods [35, 34, 24], 3 ReID methods with human-parsing information [14, 30, 27, 10] and 4 holistic ReID methods with key-points information [31, 21, 29, 26].”
Learning Discriminative Features with Multiple Granularities for Person Re-Identification (2018, unknown): “Some recent deep Re-ID methods [4, 5, 22, 27, 29, 30, 36] have achieved breakthrough with high-level identification rates and mean average precision.”
Interaction-And-Aggregation Network for Person Re-Identification (2019, result): “It is noted that: (1) The gaps between our results and the spatial alignment methods (Spindle [59], AACN [54] and PSE [35]) that incorporate an external part detection sub-network are significant: about 10% improvement on top-1 accuracy and mAP.”
Batch Coherence-Driven Network for Part-Aware Person Re-Identification (2020, background): “1, part misalignment frequently occurs in pedestrian images; this is caused by variations in viewpoint and human pose [22], [23], as well as errors in pedestrian detection.”
Identity-Guided Human Semantic Parsing for Person Re-Identification (2020, background): “Many works employ extra semantic in terms of part/pose to locate body parts [6, 27, 29, 30, 32, 34, 40, 46, 49, 56] and try to achieve the pixel-level alignment.”
Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer (2021, methodology): “Existing ReID methods can be summarized to hand-crafted descriptors [47, 23], metric learning methods [56, 20, 24] and deep learning methods[38, 25, 33, 35, 45, 52, 19, 21, 34, 26, 22].”