Instance-Level Few-Shot Learning With Class Hierarchy Mining.

Few-shot learning is proposed to tackle the problem of scarce training data in novel classes. However, prior works in instance-level few-shot learning have paid less attention to effectively utilizing the relationship between categories. In this paper, we exploit the hierarchical information to leverage discriminative and relevant features of base classes to effectively classify novel objects.

PAC-Bayes Meta-Learning With Implicit Task-Specific Posteriors.

We introduce a new and rigorously-formulated PAC-Bayes meta-learning algorithm that solves few-shot learning. Our proposed method extends the PAC-Bayes framework from a single-task setting to the meta-learning multiple-task setting to upper-bound the error evaluated on any, even unseen, tasks and samples. We also propose a generative-based approach to estimate the posterior of task-specific model parameters more expressively compared to the usual assumption based on a multivariate normal distribution with a diagonal covariance matrix.

Multimodal Mutual Information Maximization: A Novel Approach for Unsupervised Deep Cross-Modal Hashing.

In this article, we adopt the maximizing mutual information (MI) approach to tackle the problem of unsupervised learning of binary hash codes for efficient cross-modal retrieval. We proposed a novel method, dubbed cross-modal info-max hashing (CMIMH). First, to learn informative representations that can preserve both intramodal and intermodal similarities, we leverage the recent advances in estimating variational lower bound of MI to maximizing the MI between the binary representations and input features and between binary representations of different modalities.

Camouflaged Instance Segmentation In-the-Wild: Dataset, Method, and Benchmark Suite.

This paper pushes the envelope on decomposing camouflaged regions in an image into meaningful components, namely, camouflaged instances. To promote the new task of camouflaged instance segmentation of in-the-wild images, we introduce a dataset, dubbed CAMO++, that extends our preliminary CAMO dataset (camouflaged object segmentation) in terms of quantity and diversity. The new dataset substantially increases the number of images with hierarchical pixel-wise ground truths.

Big data directed acyclic graph model for real-time COVID-19 twitter stream detection.

Every day, large-scale data are continuously generated on social media as streams, such as Twitter, which inform us about all events around the world in real-time. Notably, Twitter is one of the effective platforms to update countries leaders and scientists during the coronavirus (COVID-19) pandemic. Other people have also used this platform to post their concerns about the spread of this virus and a rapid increase of death cases globally.

Unsupervised Deep Cross-modality Spectral Hashing.

This paper presents a novel framework, namely Deep Cross-modality Spectral Hashing (DCSH), to tackle the unsupervised learning problem of binary hash codes for efficient cross-modal retrieval. The framework is a two-step hashing approach which decouples the optimization into (1) binary optimization and (2) hashing function learning. In the first step, we propose a novel spectral embedding-based algorithm to simultaneously learn single-modality and binary cross-modality representations.

Multilevel Analysis of 24-Hour Blood Pressure, Heart Rate, and Associated Factors among Police Officers in Hanoi, Vietnam.

Background: Due to long-hour outdoor working environment, policemen have been subjected to tremendous health risks including blood pressure (BP) and heart rate (HR). In tropical countries, the temperature is extremely harsh which may get peak at above 40 Celsius degrees or drops under 8 Celsius degrees. However, the existing data on the effects of weather variation on BP and HR among police task force has been scarce in Vietnam.

Deterministic Approximate Methods for Maximum Consensus Robust Fitting.

Maximum consensus estimation plays a critically important role in several robust fitting problems in computer vision. Currently, the most prevalent algorithms for consensus maximization draw from the class of randomized hypothesize-and-verify algorithms, which are cheap but can usually deliver only rough approximate solutions. On the other extreme, there are exact algorithms which are exhaustive search in nature and can be costly for practical-sized inputs.

Simultaneous Feature Aggregating and Hashing for Compact Binary Code Learning.

Representing images by compact hash codes is an attractive approach for large-scale content-based image retrieval. In most state-of-the-art hashing-based image retrieval systems, for each image, local descriptors are first aggregated as a global representation vector. This global vector is then subjected to a hashing function to generate a binary hash code.

Semantic Prior Analysis for Salient Object Detection.

Salient object detection aims to detect the main objects in the given image. In this paper, we proposed an approach that integrates semantic priors into the salient object detection process. The method first obtains an explicit saliency map that is refined by the explicit semantic priors learned from data.

On-Device Scalable Image-Based Localization via Prioritized Cascade Search and Fast One-Many RANSAC.

We present the design of an entire on-device system for large-scale urban localization using images. The proposed design integrates compact image retrieval and 2D-3D correspondence search to estimate the location in extensive city regions. Our design is GPS agnostic and does not require network connection.

Embedding Based on Function Approximation for Large Scale Image Search.

The objective of this paper is to design an embedding method that maps local features describing an image (e.g., SIFT) to a higher dimensional representation useful for the image retrieval problem.

Early melanoma diagnosis with mobile imaging.

We research a mobile imaging system for early diagnosis of melanoma. Different from previous work, we focus on smartphone-captured images, and propose a detection system that runs entirely on the smartphone. Smartphone-captured images taken under loosely-controlled conditions introduce new challenges for melanoma detection, while processing performed on the smartphone is subject to computation and memory constraints.