Search Results for author:
Found 17 papers, 3 papers with code
Gesture-based Bootstrapping for Egocentric Hand Segmentation
Concretely, our approach uses two convolutional neural networks: (1) a gesture network that uses pre-defined motion information to detect the hand region; and (2) an appearance network that learns a person specific model of the hand region based on the output of the gesture network.
A Structured Model For Action Detection
A dominant paradigm for learning-based approaches in computer vision is training generic models, such as ResNet for image recognition, or I3D for video understanding, on large datasets and allowing them to discover the optimal representation for the problem at hand.
A Study on Action Detection in the Wild
In this work we study the problem of action detection in a highly-imbalanced dataset.
Towards Safety-Aware Computing System Design in Autonomous Vehicles
To address this issue, we propose a `safety score' as a primary metric for measuring the level of safety in AV computing system design.
Diagnosing the Environment Bias in Vision-and-Language Navigation
Vision-and-Language Navigation (VLN) requires an agent to follow natural-language instructions, explore the given environments, and reach the desired target locations.
Spectral Clustering with Smooth Tiny Clusters
We first divide objects into a great many tiny clusters.
Discovering Hidden Physics Behind Transport Dynamics
To help with identifiability, we develop an advection-diffusion simulator which allows pre-training of our model by supervised learning using the velocity and diffusion tensor fields.
Lighting Enhancement Aids Reconstruction of Colonoscopic Surfaces
In this work we focus on the lighting problem in colonoscopy videos.
How Frequency Effect Graph Neural Networks
Based on the frequency principle on GNNs, we present a novel powerful GNNs framework, Multi-Scale Frequency Enhanced Graph Neural Networks (MSF-GNNs) which considers multi-scale representations from wavelet decomposition.
ColDE: A Depth Estimation Framework for Colonoscopy Reconstruction
Aiming to fundamentally improve the depth estimation quality for colonoscopy 3D reconstruction, in this work we have designed a set of training losses to deal with the special challenges of colonoscopy data.
Doctor Recommendation in Online Health Forums via Expertise Learning
Huge volumes of patient queries are daily generated on online health forums, rendering manual doctor allocation a labor-intensive task.
A Multi-level Alignment Training Scheme for Video-and-Language Grounding
To solve video-and-language grounding tasks, the key is for the network to understand the connection between the two modalities.
UmeTrack: Unified multi-view end-to-end hand tracking for VR
In this paper, we present a unified end-to-end differentiable framework for multi-view, multi-frame hand tracking that directly predicts 3D hand pose in world space.
Latent Prompt Tuning for Text Summarization
In this paper, we propose Lotus (shorthand for Latent Prompt Tuning for Summarization), which is a single model that can be applied in both controlled and uncontrolled (without control signals) modes.
A Surface-normal Based Neural Framework for Colonoscopy Reconstruction
Reconstructing a 3D surface from colonoscopy video is challenging due to illumination and reflectivity variation in the video frame that can cause defective shape predictions.
Contrastive Prompt Learning-based Code Search based on Interaction Matrix
However, existing code search methods still suffer from two performance constraints: inadequate semantic representation and the semantic gap between natural language (NL) and programming language (PL).
#HowYouTagTweets: Learning User Hashtagging Preferences via Personalized Topic Attention
It is hypothesized that one’s interests in a hashtag are related with what they said before (user history) and the existing posts present the hashtag (hashtag contexts).
