activity
20192022
most citedMask-Guided Attention Network for Occluded Pedestrian Detection

36 citations · 101 across the 10 of their papers we have counts for

collaborators

12 papers

cs.CV20225 cited

An Investigation into Whitening Loss for Self-supervised Learning

Xi Weng, Lei Huang, Lei Zhao +3

A desirable objective in self-supervised learning (SSL) is to avoid feature collapse. Whitening loss guarantees collapse avoidance by minimizing the distance between embeddings of…

cs.CV20221 cited

PS-ARM: An End-to-End Attention-aware Relation Mixer Network for Person Search

Mustansar Fiaz, Hisham Cholakkal, Sanath Narayan +2

Person search is a challenging problem with various real-world applications, that aims at joint person detection and re-identification of a query person from uncropped gallery imag…

cs.CV2022

CMR3D: Contextualized Multi-Stage Refinement for 3D Object Detection

Dhanalaxmi Gaddam, Jean Lahoud, Fahad Shahbaz Khan +2

Existing deep learning-based 3D object detectors typically rely on the appearance of individual objects and do not explicitly pay attention to the rich contextual information of th…

cs.CV2022

PSTR: End-to-End One-Step Person Search With Transformers

Jiale Cao, Yanwei Pang, Rao Muhammad Anwer +4

We propose a novel one-step transformer-based person search framework, PSTR, that jointly performs person detection and re-identification (re-id) in a single architecture. PSTR com…

cs.CV20223 cited

Energy-based Latent Aligner for Incremental Learning

K J Joseph, Salman Khan, Fahad Shahbaz Khan +2

Deep learning models tend to forget their earlier knowledge while incrementally learning new tasks. This behavior emerges because the parameter updates optimized for the new tasks…

cs.CV20222 cited

Video Instance Segmentation via Multi-scale Spatio-temporal Split Attention Transformer

Omkar Thawakar, Sanath Narayan, Jiale Cao +6

State-of-the-art transformer-based video instance segmentation (VIS) approaches typically utilize either single-scale spatio-temporal features or per-frame multi-scale features dur…