On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,181 papers · 148 categories

Trend · papers per month

count % of corpus

7 results for “re-id”

Pose-Normalized Image Generation for Person Re-identificationcs.CV

Generates realistic person images for re-id, overcoming pose variations.

problem Lack of cross-view paired training data and pose variations in person re-identification.

method Pose-normalization GAN (PN-GAN) for generating images conditioned on pose.

result Synthesized images enable learning invariant features free of pose variations.

Person Re-Identification Generative Adversarial Networks Pose Normalization Transfer Learning Deep Learning

2017-12-06abs ↗pdf ↗

Beta-SOD detects and corrects noisy object re-identification using cosine similarity and Beta mixtures.

problem Noisy object re-identification in image datasets.

method Reframed Re-ID as a similarity task, using Siamese networks and Beta mixture models.

result Superior performance in noisy conditions compared to state-of-the-art methods.

object re-identification noise de-noising beta mixtures cosine similarity Siamese networks

2025-09-10abs ↗pdf ↗

Real-time Person Re-identification at the Edge: A Mixed Precision Approachcs.LG

MobileNet-v2 improves re-ID on edge devices with mixed precision.

problem Real-time person re-identification in edge devices with limited resources.

method Mixed precision training (FP32 and FP16) for MobileNet-v2 on edge nodes.

result Mixed precision training improves inference throughput and reduces power consumption.

person re-identification MobileNet-v2 mixed precision real-time edge devices

2019-08-19abs ↗pdf ↗

Jointly Attentive Spatial-Temporal Pooling Networks for Video-based Person Re-Identificationcs.CV

ASTPN improves video-based person re-identification by jointly attending to spatial and temporal features.

problem Video-based person re-identification in surveillance and HCI.

method Joint Spatial and Temporal Attention Pooling Network (ASTPN).

result ASTPN outperforms state-of-the-art methods on multiple datasets.

person re-identification video spatial-temporal attention pooling re-id

2017-08-03abs ↗pdf ↗

PRISM: Person Re-Identification via Structured Matchingcs.CV

Person re-identification (re-id), an emerging problem in visual surveillance, deals with maintaining entities of individuals whilst they traverse various locations surveilled by a camera network. From a visual perspective re-id is challenging due to significant changes in visual appearance of individuals in cameras wit…

2014-06-13abs ↗pdf ↗

A simple unsupervised approach for cross-domain person re-identification.

problem Challenges in domain adaptation for person re-identification.

method Self-similarity Grouping (SSG) approach to learn pseudo identities from unlabeled samples.

result Significant improvement in mAP performance compared to state-of-the-art methods.

person re-identification unsupervised learning domain adaptation self-similarity grouping open set setting

2018-11-26abs ↗pdf ↗

Large Margin Learning in Set to Set Similarity Comparison for Person Re-identificationcs.CV

Paper proposes a deep learning method for person re-identification using set to set distance.

problem Matching images of the same person across different camera views with large appearance variations.

method Uses deep learning to model set to set (S2S) distance, focusing on intra-class compactness and inter-class separation.

result The method effectively finds matched targets in video galleries, outperforming state-of-the-art approaches.

person re-identification set to set distance deep learning deep convolutional neural network margin learning

2017-08-18abs ↗pdf ↗