Recent advances in deep learning have provided significant
improvements in the ability to understand visual content.
Mainstream computer vision research often gives little
consideration to computation time, resource requirements, and
constraints such as energy consumption, memory footprint and
model size, or carbon emission. As computer vision is
increasingly deployed in resource-limited systems (such as
mobile phones, wearable devices, Internet of Things, autonomous
aerial vehicles), addressing all of these metrics becomes
essential. In this year’s ECV workshop, the topics of interest
include but are not limited to the following:
Topics:
- Mobile Generative vs Discriminative models
-
Augmented and Virtual Reality for computer vision, such as
image and video synthesis, object tracking, object
recognition, style transfer
-
Integration of large language models (LLM) and computer
vision, such as language-guided synthesis of images or videos;
as well as image understanding via Vision-Language Models.
-
Applications of computer vision running on mobile or wearable
devices
- Training on mobile devices
- User experience of computer vision
- Efficient Foundation Models
-
Compact and efficient architectures for foundation models,
such as Vision-Language Models, Generative Adversarial
Networks (GANs), Autoregressive models, Denoising
Diffusion Probabilistic Models (DDPMs) and Multi-Modal
Language models.
-
Efficient generative architecture search algorithms for
generative model tasks (domain adaptation, style
transfer,Latency-aware loss design for efficient model
training)
- Tunable efficiency-accuracy tradeoffs
- Efficient Neural Architecture, Compression, Quantization
and Hardware Acceleration
-
Compact and efficient neural network architecture design
-
Efficient neural architecture search algorithms for
different vision tasks (detection, segmentation,
generative models, etc.)
- Hardware accelerators to support computer vision
- Hardware-software codesign for computer vision
- Data-Efficient Learning
-
Methods, algorithms, systems that improves data efficiency
of deep learning
-
Different learning modalities (e.g., supervised,
self-supervised, reinforcement) that can improve
efficiency for computer vision
-
Zero-shot, few-shots learning, language-supervised
learning
- Open-set recognition, detection, and segmentation
- Efficient 3D models
- Efficient models for 3D understanding
- Efficient neural rendering
Speakers and Topics:
Name | Organization | Topic |
---|
Song Han
| MIT | Efficient Multi-modal LLM on the Edge |
Xianming Liu
| Xpeng |
Scaling Up Autonomous Driving with Large Foundation
Models
|
Mergen Nachin
| Meta | Low power LLM Deployment at scale with PyTorch |
Yan Deng
Keli Cheng
| Qualcomm |
Real-Time Photo-Realistic Gaussian Splatting Avatar on
the Edge
|
Xiaolong Wang
| UC San Diego | Efficient On Device LLMs for Robotics |
Jim Fan
| NVIDIA |
The Role of Foundation Models in Simulation and Control
|
Workshop Schedule (8AM to noon or 1-5PM waiting for CVPR to
confirm)
Time | Topic |
---|
08:00AM | Welcome by Organizers |
08:05AM | Song Han |
08:30AM | Xianming Liu |
08:55AM | Mergen Nachin |
09:20AM | Yan Deng, Keli Cheng |
09:45AM | Break |
10:00AM | Xiaolong Wang |
10:25AM | Jim Fan |
10:50AM | Presentations of Competition Winners |
10:50-11:00AM |
Introduction and summary talk from LPCVC organizers
|
11:00-11:45AM | Winners of Each Track (15 minutes per track) |
11:45AM | Discussion and QA |
12:00PM | Adjourn |
Organizer:
Name | Organization | Email |
---|
(Primary contact) Shuai Zhang | Qualcomm Technologies, Inc. | shuazhan@qti.qualcomm.com |
George K. Thiruvathukal | Loyola University Chicago | gthiruvathukal@luc.edu |
Yung-Hsiang Lu | Purdue University | yunglu@purdue.edu |
Mooi Choo Chuah | Lehigh University | mcc7@lehigh.edu |
Pavlo Molchanov | NVIDIA | pmolchanov@NVIDIA.com |
Hongxu (Danny) Yin | NVIDIA | dannyy@NVIDIA.com |
Ning Bi | Qualcomm Technologies, Inc. | nbi@qti.qualcomm.com |
Krishna Sridhar | Qualcomm Technologies, Inc. | srsr@qti.qualcomm.com |
Fatih Porikli | Qualcomm Technologies, Inc. | fporikli@qti.qualcomm.com |
Technical Program Committee:
Name | Organization | Email |
---|
Bo Lang (PhD student) | Lehigh University | bol221@lehigh.edu |
Amirhossein Habibian | Qualcomm Technologies, Inc. | ahabibia@qti.qualcomm.com |
Ashwin Murthy | Qualcomm Technologies, Inc. | ashwmurt@qti.qualcomm.com |
Xiao Hu | Qualcomm Technologies, Inc. | hux@qti.qualcomm.com |
Taotao Jing | Qualcomm Technologies, Inc. | tjing@qti.qualcomm.com |
Xin Li | Qualcomm Technologies, Inc. | lxi@qti.qualcomm.com |
Gaowen Liu | Cisco Systems | gaoliu@cisco.com |
Sifei Liu | NVIDIA | sifeil@NVIDIA.com |
Abhinav Goel | NVIDIA | abgoel@NVIDIA.com |
Jaeyoun Kim | Google | jaeyounkim@google.com |
Joe Spisak | Meta | jspisak@meta.com |
Bichen Wu | Meta | wbc@meta.com |
Weiwei Li | Xpeng | weiweil@xiaopeng.com |
Yamini Nimmagadda | Intel | yamini.nimmagadda@intel.com |