Search Results for author:
Found 16 papers, 5 papers with code
Prompt-driven Universal Model for View-Agnostic Echocardiography Analysis
Echocardiography segmentation for cardiac analysis is time-consuming and resource-intensive due to the variability in image quality and the necessity to process scans from various standard views.
Optimal Order Execution subject to Reservation Strategies under Execution Risk
The strategies that the agent is allowed to deploy is subject to a benchmark, referred to as the reservation strategy, regulated by the client.
Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning
Moreover, we argue that object localization and description generation require different levels of scene understanding, which could be challenging for a shared set of queries to capture.
OpenInst: A Simple Query-Based Method for Open-World Instance Segmentation
Fortunately, we have identified two observations that help us achieve the best of both worlds: 1) query-based methods demonstrate superiority over dense proposal-based methods in open-world instance segmentation, and 2) learning localization cues is sufficient for open world instance segmentation.
Depth-Assisted ResiDualGAN for Cross-Domain Aerial Images Semantic Segmentation
Generative methods are common approaches to minimizing the domain gap of aerial images which improves the performance of the downstream tasks, e. g., cross-domain semantic segmentation.
Deep ensemble learning for segmenting tuberculosis-consistent manifestations in chest radiographs
We observed that the stacking ensemble demonstrated superior segmentation performance (Dice score: 0. 5743, 95% confidence interval: (0. 4055, 0. 7431)) compared to the individual constituent models and other ensemble methods.
Attention Concatenation Volume for Accurate and Efficient Stereo Matching
Stereo matching is a fundamental building block for many vision and robotics applications.
Ranked #1 on
Stereo Depth Estimation
on Spring
ResiDualGAN: Resize-Residual DualGAN for Cross-Domain Remote Sensing Images Semantic Segmentation
The performance of a semantic segmentation model for remote sensing (RS) images pretrained on an annotated dataset would greatly decrease when testing on another unannotated dataset because of the domain gap.
Feature-Level Collaboration: Joint Unsupervised Learning of Optical Flow, Stereo Depth and Camera Motion
In this paper, we show that effective feature-level collaboration of the networks for the three respective tasks could achieve much greater performance improvement for all three tasks than only loss-level joint optimization.
Solve routing problems with a residual edge-graph attention neural network
In this paper, an end-to-end deep reinforcement learning framework is proposed to solve this type of combinatorial optimization problems.
Nuclear reactions in artificial traps
Coupled-channel two-particle systems bound by a harmonic trap are discussed in the present paper.
Nuclear Theory High Energy Physics - Lattice High Energy Physics - Phenomenology
Charged particles interaction in both a finite volume and a uniform magnetic field
A formalism for describing charged particles interaction in both a finite volume and a uniform magnetic field is presented.
Quantization
High Energy Physics - Lattice
High Energy Physics - Phenomenology
Generator and Critic: A Deep Reinforcement Learning Approach for Slate Re-ranking in E-commerce
In this paper, we present a novel Generator and Critic slate re-ranking approach, where the Critic evaluates the slate and the Generator ranks the items by the reinforcement learning approach.
ScenarioSA: A Large Scale Conversational Database for Interactive Sentiment Analysis
Existing sentiment analysis approaches are insufficient in modelling the interactions among people.
Hybrid evolutionary algorithm with extreme machine learning fitness function evaluation for two-stage capacitated facility location problem
This paper considers the two-stage capacitated facility location problem (TSCFLP) in which products manufactured in plants are delivered to customers via storage depots.
Parallel machine scheduling with step deteriorating jobs and setup times by a hybrid discrete cuckoo search algorithm
Due to its NP-hard nature, a hybrid discrete cuckoo search algorithm is proposed to solve this problem.
