Amir Ghodrati
9 papers · 2015–2025 · 4 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 ↑
🐣 Hot Topic Early Bird 🏃 Academic Marathon · Half 🌉 Interdisciplinary Bridge · Bronze 🌍 Conference Polyglot · Bronze 🗺️ Taxonomy Completionist (25)
🧬
Topic Evolution
🗃️
Keyword Collector
(62)
Top co-authors
Research topics
Deep Learning
(8)
Computer Vision
(7)
Machine Learning
(7)
Application Areas
(5)
Processing
(5)
Learning Types · Deep Learning
(4)
Analysis
(3)
Core Methods
(3)
Optimization & Theory
(3)
Architectures
(2)
Generation
(2)
Models
(2)
Artificial Intelligence
(1)
Core AI
(1)
Learning Types · Machine Learning
(1)
Keywords
video understanding
(4)
efficient computing
(3)
efficient inference
(2)
model compression
(2)
video segmentation
(2)
zero-shot learning
(2)
semantic segmentation
(2)
feature extraction
(1)
video recognition
(1)
action recognition
(1)
video generation
(1)
weakly supervised learning
(1)
model distillation
(1)
multimodal learning
(1)
object detection
(1)
conditional computation
(1)
text-to-image generation
(1)
image editing
(1)
computer vision
(1)
vision transformer
(1)
Papers
Mobile Video Diffusion
ICCV 2025
Clockwork Diffusion: Efficient Generation With Model-Step Distillation
CVPR 2024
Skip-Attention: Improving Vision Transformers by Paying Less Attention
ICLR 2024
SALISA: Saliency-Based Input Sampling for Efficient Video Object Detection
ECCV 2022
FrameExit: Conditional Early Exiting for Efficient Video Recognition
CVPR 2021
ActionBytes: Learning From Trimmed Videos to Localize Actions
CVPR 2020
Actor and Action Video Segmentation From a Sentence
CVPR 2018
DeepProposal: Hunting Objects by Cascading Deep Convolutional Layers
ICCV 2015
Modeling Video Evolution for Action Recognition
CVPR 2015