Hisham Cholakkal

28

Papers

95

Total Citations

Papers (28)

Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery

Semi-supervised Open-World Object Detection

TAViS: Text-bridged Audio-Visual Segmentation with Foundation Models

GLaMM: Pixel Grounding Large Multimodal Model

Bidirectional Reciprocative Information Communication for Few-Shot Semantic Segmentation

Backtracking ScSPM Image Classifier for Weakly Supervised Top-Down Saliency

Object Counting and Instance Segmentation With Image-Level Supervision

D2Det: Towards High Quality Object Detection and Instance Segmentation

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

Discriminative Co-Saliency and Background Mining Transformer for Co-Salient Object Detection

Person Image Synthesis via Denoising Diffusion Model

Learning Rich Features at High-Speed for Single-Shot Object Detection

3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization

Enriched Feature Guided Refinement Network for Object Detection

Handwriting Transformers

D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations

Generative Multiplane Neural Radiance for 3D-Aware Image Generation

Multi-grained Temporal Prototype Learning for Few-shot Video Object Segmentation

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

Count- and Similarity-aware R-CNN for Pedestrian Detection

Fixing Localization Errors to Improve Image Classification

DoodleFormer: Creative Sketch Drawing with Transformers

Video Instance Segmentation via Multi-Scale Spatio-Temporal Split Attention Transformer

All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages

Adapting In-Domain Few-Shot Segmentation to New Domains without Source Domain Retraining

DEFT: Decompositional Efficient Fine-Tuning for Text-to-Image Models

NeurIPS 2025arXiv

Handling Data Heterogeneity via Architectural Design for Federated Visual Recognition

3D Indoor Instance Segmentation in an Open-World