Related papers: Deep Adaptive Temporal Pooling for Activity Recogn…

Domain adaptation for object detection (DAOD) has recently drawn much attention owing to its capability of detecting target objects without any annotations. To tackle the problem, previous works focus on aligning features extracted from…

Unsupervised domain adaptation (UDA) methods have been broadly utilized to improve the models' adaptation ability in general computer vision. However, different from the natural images, there exist huge semantic gaps for the nuclei from…

When a deep neural network is trained on data with only image-level labeling, the regions activated in each image tend to identify only a small region of the target object. We propose a method of using videos automatically harvested from…

Meta-learning aims to train models that can generalize to new tasks with limited labeled data by extracting shared features across diverse task datasets. Additionally, it accounts for prediction uncertainty during both training and…

Identifying unusual driving behaviors exhibited by drivers during driving is essential for understanding driver behavior and the underlying causes of crashes. Previous studies have primarily approached this problem as a classification task,…

Deep tabular models have demonstrated remarkable success on i.i.d. data, excelling in a variety of structured data tasks. However, their performance often deteriorates under temporal distribution shifts, where trends and periodic patterns…

Visual tempo characterizes the dynamics and the temporal scale of an action. Modeling such visual tempos of different actions facilitates their recognition. Previous works often capture the visual tempo through sampling raw videos at…

Recently, the rise of large-scale vision-language pretrained models like CLIP, coupled with the technology of Parameter-Efficient FineTuning (PEFT), has captured substantial attraction in video action recognition. Nevertheless, prevailing…

Since autonomous driving systems usually face dynamic and ever-changing environments, continual test-time adaptation (CTTA) has been proposed as a strategy for transferring deployed models to continually changing target domains. However,…

Learning domain adaptive policies that can generalize to unseen transition dynamics, remains a fundamental challenge in learning-based control. Substantial progress has been made through domain representation learning to capture…

Temporal action segmentation in untrimmed videos has gained increased attention recently. However, annotating action classes and frame-wise boundaries is extremely time consuming and cost intensive, especially on large-scale datasets. To…

Graph neural networks (GNN) have been proven to be mature enough for handling graph-structured data on node-level graph representation learning tasks. However, the graph pooling technique for learning expressive graph-level representation…

Temporal Action Detection (TAD) is an essential and challenging topic in video understanding, aiming to localize the temporal segments containing human action instances and predict the action categories. The previous works greatly rely upon…

Tabular data is a common format for storing information in rows and columns to represent data entries and their features. Although deep neural networks have become the main approach for modeling a wide range of domains including computer…

We propose a novel locally adaptive learning estimator for enhancing the inter- and intra- discriminative capabilities of Deep Neural Networks, which can be used as improved loss layer for semantic image segmentation tasks. Most loss layers…

Deep neural networks are typically trained by uniformly sampling large datasets across epochs, despite evidence that not all samples contribute equally throughout learning. Recent work shows that progressively reducing the amount of…

Recent successes of Deep Neural Networks (DNNs) in a variety of research tasks, however, heavily rely on the large amounts of labeled samples. This may require considerable annotation cost in real-world applications. Fortunately, active…

Existing video domain adaption (DA) methods need to store all temporal combinations of video frames or pair the source and target videos, which are memory cost expensive and can't scale up to long videos. To address these limitations, we…

Deep Neural Networks (DNNs) and Convolutional Neural Networks (CNNs) are useful for many practical tasks in machine learning. Synaptic weights, as well as neuron activation functions within the deep network are typically stored with…

Multiple Object Tracking (MOT) plays an important role in solving many fundamental problems in video analysis in computer vision. Most MOT methods employ two steps: Object Detection and Data Association. The first step detects objects of…