Search Results for author:
Found 27 papers, 9 papers with code
Grounded Language-Image Pre-training
The unification brings two benefits: 1) it allows GLIP to learn from both detection and grounding data to improve both tasks and bootstrap a good grounding model; 2) GLIP can leverage massive image-text pairs by generating grounding boxes in a self-training fashion, making the learned representation semantic-rich.
Ranked #1 on
Phrase Grounding
on Flickr30k Entities Test
(using extra training data)
Forecasting battery capacity and power degradation with multi-task learning
In this paper, we propose a data-driven prognostics framework to predict both capacity and power fade simultaneously with multi-task learning.
TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers
We analogize MVS back to its nature of a feature matching task and therefore propose a powerful Feature Matching Transformer (FMT) to leverage intra- (self-) and inter- (cross-) attention to aggregate long-range context information within and across images.
Ranked #1 on
3D Reconstruction
on DTU
MegLoc: A Robust and Accurate Visual Localization Pipeline
In this paper, we present a visual localization pipeline, namely MegLoc, for robust and accurate 6-DoF pose estimation under varying scenarios, including indoor and outdoor scenes, different time across a day, different seasons across a year, and even across years.
Method Towards CVPR 2021 Image Matching Challenge
This report describes Megvii-3D team's approach towards CVPR 2021 Image Matching Workshop.
Method Towards CVPR 2021 SimLocMatch Challenge
This report describes Megvii-3D team's approach towards SimLocMatch Challenge @ CVPR 2021 Image Matching Workshop.
ELSD: Efficient Line Segment Detector and Descriptor
The line description ability of ELSD also outperforms the previous works on the line matching task.
Ranked #2 on
Line Segment Detection
on wireframe dataset
Amortized Variational Deep Q Network
Efficient exploration is one of the most important issues in deep reinforcement learning.
Recurrent Inference in Text Editing
In neural text editing, prevalent sequence-to-sequence based approaches directly map the unedited text either to the edited text or the editing operations, in which the performance is degraded by the limited source text encoding and long, varying decoding steps.
IA-MOT: Instance-Aware Multi-Object Tracking with Motion Consistency
Meanwhile, the spatial attention, which focuses on the foreground within the bounding boxes, is generated from the given instance masks and applied to the extracted embedding features.
Learning to be Global Optimizer
This paper proposes to learn a two-phase (including a minimization phase and an escaping phase) global optimization algorithm for smooth non-convex functions.
On Hyper-parameter Tuning for Stochastic Optimization Algorithms
This paper proposes the first-ever algorithmic framework for tuning hyper-parameters of stochastic optimization algorithm based on reinforcement learning.
Adaptive Structural Hyper-Parameter Configuration by Q-Learning
Tuning hyper-parameters for evolutionary algorithms is an important issue in computational intelligence.
Learning Neural Surrogate Model for Warm-Starting Bayesian Optimization
Bayesian optimization is an effective tool to optimize black-box functions and popular for hyper-parameter tuning in machine learning.
Cross-Domain Modeling of Sentence-Level Evidence for Document Retrieval
This paper applies BERT to ad hoc document retrieval on news articles, which requires addressing two challenges: relevance judgments in existing test collections are typically provided only at the document level, and documents often exceed the length that BERT was designed to handle.
Applying BERT to Document Retrieval with Birch
We present Birch, a system that applies BERT to document retrieval via integration with the open-source Anserini information retrieval toolkit to demonstrate end-to-end search over large document collections.
Eye in the Sky: Drone-Based Object Tracking and 3D Localization
Drones, or general UAVs, equipped with a single camera have been widely deployed to a broad range of applications, such as aerial photography, fast goods delivery and most importantly, surveillance.
GetNet: Get Target Area for Image Pairing
Image pairing is an important research task in the field of computer vision.
Rekall: Specifying Video Events using Compositions of Spatiotemporal Labels
Many real-world video analysis applications require the ability to identify domain-specific events in video, such as interviews and commercials in TV news broadcasts, or action sequences in film.
An Internal Learning Approach to Video Inpainting
We propose a novel video inpainting algorithm that simultaneously hallucinates missing appearance and motion (optical flow) information, building upon the recent 'Deep Image Prior' (DIP) that exploits convolutional network architectures to enforce plausible texture in static images.
Simple Applications of BERT for Ad Hoc Document Retrieval
Following recent successes in applying BERT to question answering, we explore simple applications to ad hoc document retrieval.
Ranked #2 on
Ad-Hoc Information Retrieval
on TREC Robust04
(MAP metric)
TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshes
We introduce, TextureNet, a neural network architecture designed to extract features from high-resolution signals associated with 3D surface meshes (e. g., color texture maps).
Ranked #11 on
Semantic Segmentation
on ScanNet
Exploit the Connectivity: Multi-Object Tracking with TrackletNet
Multi-object tracking (MOT) is an important and practical task related to both surveillance systems and moving camera applications, such as autonomous driving and robotic vision.
Ranked #16 on
Multi-Object Tracking
on MOT16
Evaluating Sentence-Level Relevance Feedback for High-Recall Information Retrieval
This study uses a novel simulation framework to evaluate whether the time and effort necessary to achieve high recall using active learning is reduced by presenting the reviewer with isolated sentences, as opposed to full documents, for relevance feedback.
Integrating Lexical and Temporal Signals in Neural Ranking Models for Searching Social Media Streams
To our knowledge, we are the first to integrate lexical and temporal signals in an end-to-end neural network architecture, in which existing neural ranking models are used to generate query-document similarity vectors that feed into a bidirectional LSTM layer for temporal modeling.
Exploring the Effectiveness of Convolutional Neural Networks for Answer Selection in End-to-End Question Answering
Most work on natural language question answering today focuses on answer selection: given a candidate list of sentences, determine which contains the answer.
