Mancs: A Multi-task Attentional Network with Curriculum Sampling for Person Re-Identification

By Cheng Wang, Qian Zhang, Chang Huang, Xinggang Wang. European Conference on Computer Vision, 2018

394 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/c753521ba6fb06c12369d6fff814bb704c682ef5

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

Interaction-And-Aggregation Network for Person Re-Identification (2019, neutral): “Person reID methods focus on two key points: learning a powerful feature representation for images [8, 43, 14, 44, 24, 26, 28, 42, 1] and designing an effective distance metric [32, 29, 56, 2, 57].”
Learning an Evolutionary Embedding via Massive Knowledge Distillation (2020, background): “Deep mutual learning (Zhang et al. 2018) learns collab-oratively and teaches each other between two networks to boost performance for both close-set and open-set problems.”
Context-aware Feature Generation For Zero-shot Semantic Segmentation (2020, background): “Although our contextual module looks similar to channel attention [14, 23] or full attention [41], our motivation and technical details are intrinsically different from them.”
Cluster Contrast for Unsupervised Person Re-Identification (2021, methodology): “In supervised person re-ID, the combination of triplet loss and identity loss is proved to be effective solutions to improving the re-ID performance [34, 38, 3, 2, 57, 51, 4, 12, 25].”
Omni-Scale Feature Learning for Person Re-Identification (2019, neutral): “2 Mancs [49] ECCV’18 ResNet 93.”
Attention mechanisms in computer vision: A survey (2021, neutral): “[130, 101, 123, 86, 96, 17, 84], [108, 40, 61, 166, 148, 152, 135] , [122, 14, 19, 62, 78]”
Deep Learning for Person Re-Identification: A Survey and Outlook (2020, methodology): “A Fully Attentional Block (FAB) is designed in [80] to adjust the channel-wise feature response.”
Bag of Tricks and a Strong Baseline for Deep Person Re-Identification (2019, neutral): “Attentionbased Mancs [18] 1 93.”
Relation-Aware Global Attention for Person Re-Identification (2019, background): “(a) Local attention : the attention for a feature node is determined locally, e . g ., applying a shared transformation function F on itself, i.e ., a i = F ( x i ) [32].”
Bilinear Attention Networks for Person Retrieval (2019, methodology): “Formally, we have xz = Sigmoid ( φ ( Bi(ϕ(x)) ) ) ⊗ x. (6) Remark 2 The structure of Bi-attention without AiA is similar to the Fully Attentional Block (FAB) [43] in the sense that both types of attention keep spatial structure information of the feature map, but with a fundamental difference that o”
Memory-Based Neighbourhood Embedding for Visual Recognition (2019, neutral): “4 Mancs [42] ECCV’18 71.”
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification (2021, neutral): “3 - - Mancs [56] 93.”
ABD-Net: Attentive but Diverse Person Re-Identification (2019, neutral): “00 * Mancs [65] (2018 ECCV) 93.”