Search Results for author:
Found 41 papers, 9 papers with code
Deep Reasoning Networks for Unsupervised Pattern De-mixing with Constraint Reasoning
We introduce Deep Reasoning Networks (DRNets), an end-to-end framework that combines deep learning with constraint reasoning for solving pattern de-mixing problems, typically in an unsupervised or very-weakly-supervised setting.
TrajFlow: Multi-modal Motion Prediction via Flow Matching
Efficient and accurate motion prediction is crucial for ensuring safety and informed decision-making in autonomous driving, particularly under dynamic real-world conditions that necessitate multi-modal forecasts.
LONGER: Scaling Up Long Sequence Modeling in Industrial Recommenders
Modeling ultra-long user behavior sequences is critical for capturing both long- and short-term preferences in industrial recommender systems.
Wan: Open and Advanced Large-Scale Video Generative Models
Openness: We open-source the entire series of Wan, including source code and all models, with the goal of fostering the growth of the video generation community.
Adaptive Domain Scaling for Personalized Sequential Modeling in Recommenders
Users generally exhibit complex behavioral patterns and diverse intentions in multiple business scenarios of super applications like Douyin, presenting great challenges to current industrial multi-domain recommenders.
Dynamic High-Order Control Barrier Functions with Diffuser for Safety-Critical Trajectory Planning at Signal-Free Intersections
To further ensure driving safety in dynamic environments, the proposed DHOCBF framework dynamically adjusts to account for the movements of surrounding vehicles, offering enhanced adaptability and reduce the conservatism compared to traditional control barrier functions.
How to predict on-road air pollution based on street view images and machine learning: a quantitative analysis of the optimal strategy
Therefore, the optimal sampling strategy is to obtain SVIs at a 100m radius buffer and extract features using the averaging strategy.
Evidence and quantification of cooperation of driving agents in mixed traffic flow
This study provides the first empirical understanding of collective cooperativeness in human-driven mixed traffic and points to new possibilities to manage mixed autonomy traffic systems.
Risk-anticipatory autonomous driving strategies considering vehicles' weights, based on hierarchical deep reinforcement learning
Autonomous vehicles (AVs) have the potential to prevent accidents caused by drivers errors and reduce road traffic risks.
Divide and Conquer: Hybrid Pre-training for Person Search
To the best of our knowledge, this is the first work that investigates how to support full-task pre-training using sub-task data.
Data-driven Traffic Simulation: A Comprehensive Review
The primary objective of this paper is to review current research efforts and provide a futuristic perspective that will benefit future developments in the field.
Composer: Creative and Controllable Image Synthesis with Composable Conditions
Recent large-scale generative models learned on big data are capable of synthesizing incredible images yet suffer from limited controllability.
Grouped Adaptive Loss Weighting for Person Search
A straightforward solution is to manually assign different weights to different tasks, compensating for the diverse convergence rates.
Monitoring Vegetation From Space at Extremely Fine Resolutions via Coarsely-Supervised Smooth U-Net
This poses a challenging coarsely-supervised regression (or downscaling) task; at training time, we only have SIF labels at a coarse resolution (3km), but we want to predict SIF at much finer spatial resolutions (e. g. 30m, a 100x increase).
PoseTrack21: A Dataset for Person Search, Multi-Object Tracking and Multi-Person Pose Tracking
Current research evaluates person search, multi-object tracking and multi-person pose estimation as separate tasks and on different datasets although these tasks are very akin to each other and comprise similar sub-tasks, e. g. person detection or appearance-based association of detected persons.
Keypoint Message Passing for Video-based Person Re-Identification
Video-based person re-identification (re-ID) is an important technique in visual surveillance systems which aims to match video snippets of people captured by different cameras.
Representation Learning
Video-Based Person Re-Identification
Automating Crystal-Structure Phase Mapping: Combining Deep Learning with Constraint Reasoning
DRNets compensate for the limited data by exploiting and magnifying the rich prior knowledge about the thermodynamic rules governing the mixtures of crystals with constraint reasoning seamlessly integrated into neural network optimization.
Model comparison of DBD-PA-induced body force in quiescent air and separated flow over NACA0015
The D-D models generate momentarily higher body force in the positive-going phase of the AC power, but activate a smaller flow region than the S-H model with Dc = 0. 0117, which is given by the experiment beforehand at 7kV.
Fluid Dynamics Plasma Physics
PoseTrackReID: Dataset Description
For that reason, we present PoseTrackReID, a large-scale dataset for multi-person pose tracking and video-based person re-ID.
Deep Hurdle Networks for Zero-Inflated Multi-Target Regression: Application to Multiple Species Abundance Estimation
A key problem in computational sustainability is to understand the distribution of species across landscapes over time.
Block-term Tensor Neural Networks
Deep neural networks (DNNs) have achieved outstanding performance in a wide range of applications, e. g., image classification, natural language processing, etc.
Norm-Aware Embedding for Efficient Person Search
Person Search is a practically relevant task that aims to jointly solve Person Detection and Person Re-identification (re-ID).
VerSe: A Vertebrae Labelling and Segmentation Benchmark for Multi-detector CT Images
Two datasets containing a total of 374 multi-detector CT scans from 355 patients were prepared and 4505 vertebrae have individually been annotated at voxel-level by a human-machine hybrid algorithm (https://osf. io/nqjyw/, https://osf. io/t98fz/).
Task-Based Learning via Task-Oriented Prediction Network with Applications in Finance
Real-world applications often involve domain-specific and task-based performance objectives that are not captured by the standard machine learning losses, but are critical for decision making.
Deep Reasoning Networks: Thinking Fast and Slow, for Pattern De-mixing
We introduce Deep Reasoning Networks (DRNets), an end-to-end framework that combines deep learning with reasoning for solving pattern de-mixing problems, typically in an unsupervised or weakly-supervised setting.
Two-Stream CNN with Loose Pair Training for Multi-modal AMD Categorization
The CNN's fusion layer is tailored to the need of fusing information from the fundus and OCT streams.
Deep Reasoning Networks: Thinking Fast and Slow
At a high level, DRNets encode a structured latent space of the input data, which is constrained to adhere to prior knowledge by a reasoning module.
Automatic Detection and Compression for Passive Acoustic Monitoring of the African Forest Elephant
In this work, we consider applying machine learning to the analysis and compression of audio signals in the context of monitoring elephants in sub-Saharan Africa.
How to "DODGE" Complex Software Analytics?
Machine learning techniques applied to software engineering tasks can be improved by hyperparameter optimization, i. e., automatic tools that find good settings for a learner's control parameters.
Bias Reduction via End-to-End Shift Learning: Application to Citizen Science
Citizen science projects are successful at gathering rich datasets for various applications.
Hybrid Neural Attention for Agreement/Disagreement Inference in Online Debates
Inferring the agreement/disagreement relation in debates, especially in online debates, is one of the fundamental tasks in argumentation mining.
Person Search via A Mask-Guided Two-Stream CNN Model
In this work, we tackle the problem of person search, which is a challenging task consisted of pedestrian detection and person re-identification~(re-ID).
End-to-End Learning for the Deep Multivariate Probit Model
The multivariate probit model (MVP) is a popular classic model for studying binary responses of multiple entities.
Texture Segmentation Based Video Compression Using Convolutional Neural Networks
There has been a growing interest in using different approaches to improve the coding efficiency of modern video codec in recent years as demand for web-based video consumption increases.
BT-Nets: Simplifying Deep Neural Networks via Block Term Decomposition
Recently, deep neural networks (DNNs) have been regarded as the state-of-the-art classification methods in a wide range of applications, especially in image classification.
Learning Compact Recurrent Neural Networks with Block-Term Tensor Decomposition
On three challenging tasks, including Action Recognition in Videos, Image Captioning and Image Generation, BT-RNN outperforms TT-RNN and the standard RNN in terms of both prediction accuracy and convergence rate.
Multi-Entity Dependence Learning with Rich Context via Conditional Variational Auto-encoder
Multi-Entity Dependence Learning (MEDL) explores conditional correlations among multiple entities.
Deep Multi-Species Embedding
Additionally, we demonstrate the benefit of using a deep neural network to extract features within the embedding and show how they improve the predictive performance of species distribution modelling.
Relative Error Embeddings for the Gaussian Kernel Distance
A reproducing kernel can define an embedding of a data point into an infinite dimensional reproducing kernel Hilbert space (RKHS).
