Graduate

SCIEN Talk: Perceptual Modeling with Multimodal Sensing

Topic: 
Perceptual Modeling with Multimodal Sensing
Abstract / Description: 

The research of human perception has enabled many visual applications in computer graphics that efficiently utilize computation resources to deliver a high quality experience within the limitations of the hardware. Beyond vision, humans perceive their surrounding using variety of senses to build a mental model of the world and act upon it. This mental image is often incomplete or incorrect which may have safety implications. As we cannot directly see inside the head, we need to read indirect signals projected outside. In the first part of the talk I will show how perceptual modeling can be used to overcome and exploit limitations of one specific human sense - the vision. Then, I will describe how we can build sensors to observe other human interactions connected first with physical touch and then with eye gaze patterns. Finally, I will outline how such readings can be used to teach computers to understand human behavior, to predict and to provide assistance or safety.

Date and Time: 
Wednesday, November 28, 2018 - 4:30pm
Venue: 
Packard 101

SCIEN Talk: Photo Forensics from JPEG Coding Artifacts

Topic: 
Photo Forensics from JPEG Coding Artifacts
Abstract / Description: 

The past few years have seen a startling and troubling rise in the fake-news phenomena in which everyone from individuals to state-sponsored entities produce and distribute mis-information, which is then widely promoted and disseminated on social media. The implications of fake news range from a mis-informed public to an existential threat to democracy, and horrific violence. At the same time, recent and rapid advances in machine learning are making it easier than ever to create sophisticated and compelling fake images and videos, making the fake-news phenomena even more powerful and dangerous. I will start by providing a broad overview of the field of image and video forensics and then I will describe in detail a suite of image forensic techniques that explicitly detect inconsistencies in JPEG coding artifacts.

Date and Time: 
Wednesday, November 14, 2018 - 4:30pm
Venue: 
Packard 101

SCIEN Talk: Wavefront coding techniques and resolution limits for light field microscopy

Topic: 
Wavefront coding techniques and resolution limits for light field microscopy
Abstract / Description: 

Light field microscopy is a rapid, scan-less volume imaging technique that requires only a standard wide field fluorescence microscope and a microlens array. Unlike scanning microscopes, which collect volumetric information over time, the light field microscope captures volumes synchronously in a single photographic exposure, and at speeds limited only by the frame rate of the image sensor. This is made possible by the microlens array, which focuses light onto the camera sensor so that each position in the volume is mapped onto the sensor as a unique light intensity pattern. These intensity patterns are the position-dependent point response functions of the light field microscope. With prior knowledge of these point response functions, it is possible to "decode" 3-D information from a raw light field image and computationally reconstruct a full volume. In this talk I present an optical model for light field microscopy based on wave optics that accurately models light field point response functions. I describe an algorithm that solves for volumes using a GPU-accelerated iterative algorithm, and discuss priors that are useful for reconstructing biological specimens. I then explore the diffraction limit that applies for light field microscopy, and how it gives rise to a position-dependent resolution limits for this microscope. I'll explain how these limits differ from more familiar resolution metrics commonly used in 3-D scanning microscopy, like the Rayleigh limit and the optical transfer function (OTF). Using this theory of resolution limits for the light field microscope, I explore new wavefront coding techniques that can modify the light field resolution limits and can address certain common reconstruction artifacts, at least to a degree. Certain resolution trade-offs exist that suggest that light field microscopy is just one of potentially many useful forms of computational microscopy. Finally, I describe our application of light field microscopy in neuroscience where we have used it to record calcium activity in populations of neurons within the brains of awake, behaving animals.

Date and Time: 
Wednesday, October 31, 2018 - 4:30pm
Venue: 
Packard 101

SCIEN Talk: Is it real? Deep Neural Face Reconstruction and Rendering

Topic: 
Is it real? Deep Neural Face Reconstruction and Rendering
Abstract / Description: 

A broad range of applications in visual effects, computer animation, autonomous driving, and man-machine interaction heavily depend on robust and fast algorithms to obtain high-quality reconstructions of our physical world in terms of geometry, motion, reflectance, and illumination. Especially, with the increasing popularity of virtual, augmented and mixed reality devices, there comes a rising demand for real-time and low-latency solutions.

This talk covers data-parallel optimization and state-of-the-art machine learning techniques to tackle the underlying 3D and 4D reconstruction problems based on novel mathematical models and fast algorithms. The particular focus of this talk is on self-supervised face reconstruction from a collection of unlabeled in-the-wild images. The proposed approach can be trained end-to-end without dense annotations by fusing a convolutional encoder with a differentiable expert-designed renderer and a self-supervised training loss.

The resulting reconstructions are the foundation for advanced video editing effects, such as photo-realistic re-animation of portrait videos. The core of the proposed approach is a generative rendering-to-video translation network that takes computer graphics renderings as input and generates photo-realistic modified target videos that mimic the source content. With the ability to freely control the underlying parametric face model, we are able to demonstrate a large variety of video rewrite applications. For instance, we can reenact the full head using interactive user-controlled editing and realize high-fidelity visual dubbing.

Date and Time: 
Wednesday, October 24, 2018 - 4:30pm
Venue: 
Packard 101

SCIEN Talk: Computational microscopy of dynamic order across biological scales

Topic: 
Computational microscopy of dynamic order across biological scales
Abstract / Description: 

Living systems are characterized by emergent behavior of ordered components. Imaging technologies that reveal dynamic arrangement of organelles in a cell and of cells in a tissue are needed to understand the emergent behavior of living systems. I will present an overview of challenges in imaging dynamic order at the scales of cells and tissue, and discuss advances in computational label-free microscopy to overcome these challenges.

 

Date and Time: 
Wednesday, October 17, 2018 - 4:30pm
Venue: 
Packard 101

SCIEN Talk: How to train neural networks on LiDAR point clouds

Topic: 
How to train neural networks on LiDAR point clouds
Abstract / Description: 

Accurate LiDAR classification and segmentation is required for developing critical ADAS & Autonomous Vehicles components. Mainly, its required for high definition mapping and developing perception and path/motion planning algorithms. This talk will cover best practices for how to accurately annotate and benchmark your AV/ADAS models against LiDAR point cloud ground truth training data.

 

Date and Time: 
Wednesday, October 10, 2018 - 4:30pm
Venue: 
Packard 101

EE Pumpkin Carving Contest 2018

Topic: 
EE Pumpkin Carving Contest 2018
Abstract / Description: 

You are invited to EE's Pumpkin Carving Contest. This event brings together the EE community in a friendly forum to carve the best Halloween Pumpkin. Come together with your friends/labmates/colleagues to craft the best pumpkin and be awarded EE's Pumpkin Carving Contest Winners for 2018. Your team will be eligible to win some great prizes as well!

Sign-up deadline: Wednesday, October 24!

Sign-up link: http://bit.ly/eepumpkin18

 

Contest Rules:

  • 3-4 members per team; at least two (2) members must in the EE Department.
  • Teams will have 45 minutes to complete their pumpkin. Keep in mind that the pumpkins are whole (not pre-gutted).
  • A team of judges will determine the winners based or originality/creativity, completeness and technical skill.
  • Extra points will be awarded to teams that show up in costume.
  • If you dress up, you're eligible to enter a raffle to win more prizes.

We'll provide the pumpkins, basic carving tools, and plastic aprons.
You're welcome to bring additional props/decorations for your pumpkin, feel free to bring whatever you like to decorate, embellish, or design your pumpkin.

Date and Time: 
Wednesday, October 31, 2018 - 12:30pm
Venue: 
Packard Atrium

SCIEN & EE 292E: The challenge of large-scale brain imaging

Topic: 
The challenge of large-scale brain imaging
Abstract / Description: 

Advanced optical microscopy techniques have enabled the recording and stimulation of large populations of neurons deep within living, intact animal brains. I will present a broad overview of these techniques, and discuss challenges that still remain in performing large-scale imaging with high spatio-temporal resolution, along with various strategies that are being adopted to address these challenges.

Date and Time: 
Wednesday, October 3, 2018 - 4:30pm
Venue: 
Packard 101

EE380 Computer Systems Colloquium: Efficient and Resilient Systems in the Cognitive Era

Topic: 
Efficient and Resilient Systems in the Cognitive Era
Abstract / Description: 

A focus on energy efficiency in the late CMOS design era, requires extra careful attention to system reliability and resilience to hardware-sourced errors. At the same time, the emergence of AI (cognitive) applications as a key growth segment is quite obvious. This talk will attempt to address the special challenges that next generation AI (or cognitive) systems pose, with a particular focus on next generation cognitive IoT architectures. We will discuss this primarily from the point of view of providing energy-efficient resilience in environments that are likely to have built-in vulnerability to errors. Such uncertainty stems not just from potentially error-prone (late CMOS) hardware designed for extreme efficiency, but also from algorithmic brittleness of the most prevalent forms of machine learning/deep learning (ML/DL) solution strategies today. In that context, we will briefly examine the promise of the Adaptive Swarm Intelligence (ASI) architectural paradigm that we have recently started investigating at IBM Research. This is a form of distributed or decentralized computing applied to the world of mobile cognitive IoT, backed by resilient support from back-end cloud (server) systems. In addition to examining the promises of inherent system architectural scalability and in-field, continuous learning that ASI offers, we will argue (albeit philosophically!) about why this could open the door to new models of self-aware systems that mimic cooperative and conscious problem solving in a human setting.


The Stanford EE Computer Systems Colloquium (EE380) meets on Wednesdays 4:30-5:45 throughout the academic year. Talks are given before a live audience in Room B03 in the basement of the Gates Computer Science Building on the Stanford Campus. The live talks (and the videos hosted at Stanford and on YouTube) are open to the public.

Stanford students may enroll in EE380 to take the Colloquium as a one unit S/NC class. Enrolled students are required to keep and electronic notebook or journal and to write a short, pithy comment about each of the ten lectures and a short free form evaluation of the class in order to receive credit. Assignments are due at the end of the quarter, on the last day of examinations.

EE380 is a video class. Live attendance is encouraged but not required. We (the organizers) feel that watching the video is not a substitute for being present in the classroom. Questions are encouraged.

Many past EE380 talks are available on YouTube, see the EE380 Playlist.

Date and Time: 
Wednesday, October 3, 2018 - 4:30pm
Venue: 
Gates B03

Pages

Subscribe to RSS - Graduate