hishamcholakkal
Cholakkal has diverse experiences across fundamental research, teaching, and product development in the industry.
MBUAIAbu Dhabi, UAE
Pinned Repositories
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)
hishamcholakkal's Repositories
hishamcholakkal/CountSeg
Official code for "Object counting and instance segmentation with image-level supervision", in CVPR 2019 and TPAMI 2020
hishamcholakkal/D2Det
D2Det: Towards High Quality Object Detection and Instance Segmentation (CVPR2020)
hishamcholakkal/doodleformer
DoodleFormer: Creative Sketch Drawing with Transformers (ECCV22)
hishamcholakkal/EdgeNeXt
[CADL'22, ECCVW] Official repository of paper titled "EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications".
hishamcholakkal/Handwriting-Transformers
Handwriting-Transformers (ICCV21)
hishamcholakkal/hishamcholakkal.github.io
I'm a computer vision researcher affiliated with MBZUAI
hishamcholakkal/MobiLlama
MobiLlama : Small Language Model tailored for edge devices
hishamcholakkal/MSSTS-VIS
Multi-Scale Spatio-Temporal Attention based Video Instance Segmentation (ECCV 2022)
hishamcholakkal/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
hishamcholakkal/PSTR
PSTR: End-to-End One-Step Person Search With Transformers (CVPR2022)
hishamcholakkal/SipMask
SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation (ECCV2020)
hishamcholakkal/starter-academic