hishamcholakkal Goto Github PK

countseg

Official code for "Object counting and instance segmentation with image-level supervision", in CVPR 2019 and TPAMI 2020

d2det

D2Det: Towards High Quality Object Detection and Instance Segmentation (CVPR2020)

doodleformer

DoodleFormer: Creative Sketch Drawing with Transformers (ECCV22)

edgenext

[CADL'22, ECCVW] Official repository of paper titled "EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications".

handwriting-transformers

Handwriting-Transformers (ICCV21)

hishamcholakkal.github.io

I'm a computer vision researcher affiliated with MBZUAI

mobillama

MobiLlama : Small Language Model tailored for edge devices

mssts-vis

Multi-Scale Spatio-Temporal Attention based Video Instance Segmentation (ECCV 2022)

ps-arm

Abstract. 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 images. Although, previous study focuses on rich feature information learning, it’s still hard to re- trieve the query person due to the occurrence of appearance deformations and background distractors. In this paper, we propose a novel attention- aware relation mixer (ARM) module for person search, which exploits the global relation between different local regions within RoI of a per- son and make it robust against various appearance deformations and occlusion. The proposed ARM is composed of a relation mixer block and a spatio-channel attention layer. The relation mixer block introduces a spatially attended spatial mixing and a channel-wise attended channel mixing for effectively capturing discriminative relation features within an RoI. These discriminative relation features are further enriched by intro- ducing a spatio-channel attention where the foreground and background discriminability is empowered in a joint spatio-channel space. Our ARM module is generic and it does not rely on fine-grained supervisions or topological assumptions, hence being easily integrated into any Faster R-CNN based person search methods. Comprehensive experiments are performed on two challenging benchmark datasets: CUHK-SYSU [1] and PRW [2]. Our PS-ARM achieves state-of-the-art performance on both datasets. On the challenging PRW dataset, our PS-ARM achieves an absolute gain of 5% in the mAP score over SeqNet, while operating at a comparable speed

pstr

PSTR: End-to-End One-Step Person Search With Transformers (CVPR2022)

sipmask

SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation (ECCV2020)

starter-academic