Search Results for author:
Found 17 papers, 10 papers with code
Single Domain Generalization for Crowd Counting
The existing SDG approaches are mainly for image classification and segmentation, and can hardly be extended to our case due to its regression nature and label ambiguity (i. e., ambiguous pixel-level ground truths).
Target-agnostic Source-free Domain Adaptation for Regression Tasks
Unsupervised domain adaptation (UDA) seeks to bridge the domain gap between the target and source using unlabeled target data.
A Multi-Scale Decomposition MLP-Mixer for Time Series Analysis
To handle the multi-scale temporal patterns and multivariate dependencies, we propose a novel temporal patching approach to model the time series as multi-scale patches, and employ MLPs to capture intra- and inter-patch variations and channel-wise correlations.
FIS-ONE: Floor Identification System with One Label for Crowdsourced RF Signals
To build a prediction model to identify the floor number of a new RF signal upon its measurement, conventional approaches using the crowdsourced RF signals assume that at least few labeled signal samples are available on each floor.
Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks
To achieve faster networks, we revisit popular operators and demonstrate that such low FLOPS is mainly due to frequent memory access of the operators, especially the depthwise convolution.
TVConv: Efficient Translation Variant Convolution for Layout-aware Visual Processing
Extensive experiments on face recognition show that TVConv reduces the computational cost by up to 3. 1x and improves the corresponding throughput by 2. 3x while maintaining a high accuracy compared to the depthwise convolution.
A Lightweight and Accurate Spatial-Temporal Transformer for Traffic Forecasting
The information fusion module captures the complex spatial-temporal dependency between regions.
NAS-OoD: Neural Architecture Search for Out-of-Distribution Generalization
In this work, we propose robust Neural Architecture Search for OoD generalization (NAS-OoD), which optimizes the architecture with respect to its performance on generated OoD data by gradient descent.
Ranked #1 on
Domain Generalization
on NICO Vehicle
Crowd Counting by Self-supervised Transfer Colorization Learning and Global Prior Classification
The classification branch extracts global group priors by learning correlations among image clusters.
Motion-guided Non-local Spatial-Temporal Network for Video Crowd Counting
Noting the scarcity and low quality (in terms of resolution and scene diversity) of the publicly available video crowd datasets, we have collected and built a large-scale video crowd counting datasets, VidCrowd, to contribute to the community.
Joint Demosaicking and Denoising in the Wild: The Case of Training Under Ground Truth Uncertainty
In this paper, we propose and study Wild-JDD, a novel learning framework for joint demosaicking and denoising in the wild.
A Survey on Deep Learning-based Single Image Crowd Counting: Network Design, Loss Function and Supervisory Signal
Single image crowd counting is a challenging computer vision problem with wide applications in public safety, city planning, traffic management, etc.
DecAug: Out-of-Distribution Generalization via Decomposed Feature Representation and Semantic Augmentation
To address that, we propose DecAug, a novel decomposed feature representation and semantic augmentation approach for OoD generalization.
Crowd Counting on Images with Scale Variation and Isolated Clusters
Designing a general crowd counting algorithm applicable to a wide range of crowd images is challenging, mainly due to the possibly large variation in object scales and the presence of many isolated small clusters.
DA-LSTM: A Long Short-Term Memory with Depth Adaptive to Non-uniform Information Flow in Sequential Data
In this paper, we develop a Depth-Adaptive Long Short-Term Memory (DA-LSTM) architecture, which can dynamically adjust the structure depending on information distribution without prior knowledge.
Representation Learning of Pedestrian Trajectories Using Actor-Critic Sequence-to-Sequence Autoencoder
Representation learning of pedestrian trajectories transforms variable-length timestamp-coordinate tuples of a trajectory into a fixed-length vector representation that summarizes spatiotemporal characteristics.
