Suman Saha
12 papers · 2017–2026 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
🗺️ Taxonomy Completionist (22) 🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge · Bronze
👥
Mega-Team · Squad
💎
Century Club · Bronze
Top co-authors
Research topics
Computer Vision
(7)
Analysis
(6)
Machine Learning
(5)
Application Areas
(4)
Deep Learning
(3)
Domain-Specific
(3)
Learning Types · Deep Learning
(3)
Learning Types · Machine Learning
(3)
Artificial Intelligence
(2)
Natural Language Processing
(1)
Reinforcement Learning
(1)
Core AI · Artificial Intelligence
(1)
Core AI · Computer Vision
(1)
Generation · Natural Language Processing
(1)
Generation · Computer Vision
(1)
Keywords
semantic segmentation
(4)
unsupervised domain adaptation
(3)
domain adaptation
(2)
depth estimation
(2)
instance segmentation
(2)
panoptic segmentation
(2)
knowledge distillation
(1)
data augmentation
(1)
cross-domain learning
(1)
autoregressive generation
(1)
multimodal learning
(1)
monocular depth estimation
(1)
pseudo labeling
(1)
object tracking
(1)
world model
(1)
supervised fine-tuning
(1)
domain alignment
(1)
feature aggregation
(1)
domain shift
(1)
temporal feature
(1)
Papers
Reference-Free Schema Generation for Literature Review Tables via Multi-Faceted Rewards
ACL 2026
GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control
CVPR 2025
Language-Guided Instance-Aware Domain-Adaptive Panoptic Segmentation
WACV 2025
Four Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding
ECCV 2024
EDAPS: Enhanced Domain-Adaptive Panoptic Segmentation
ICCV 2023
Exploiting Instance-Based Mixed Sampling via Auxiliary Source Domain Supervision for Domain-Adaptive Action Detection
WACV 2023
Spatio-Temporal Action Detection Under Large Motion
WACV 2023
Learning To Relate Depth and Semantics for Unsupervised Domain Adaptation
CVPR 2021
Three Ways To Improve Semantic Segmentation With Self-Supervised Depth Estimation
CVPR 2021
Reparameterizing Convolutions for Incremental Multi-Task Learning without Task Interference
ECCV 2020
AMTnet: Action-Micro-Tube Regression by End-To-End Trainable Deep Architecture
ICCV 2017
Online Real-Time Multiple Spatiotemporal Action Localisation and Prediction
ICCV 2017