Related papers: Evolution-Preserving Dense Trajectory Descriptors

In real-world applications, dynamic scenarios require the models to possess the capability to learn new tasks continuously without forgetting the old knowledge. Experience-Replay methods store a subset of the old images for joint training.…

Recently, Vision-Language-Action models (VLA) have advanced robot imitation learning, but high data collection costs and limited demonstrations hinder generalization and current imitation learning methods struggle in out-of-distribution…

The abundance of instructional videos and their narrations over the Internet offers an exciting avenue for understanding procedural activities. In this work, we propose to learn video representation that encodes both action steps and their…

Current methods for trajectory prediction operate in supervised manners, and therefore require vast quantities of corresponding ground truth data for training. In this paper, we present a novel, label-free algorithm, AutoTrajectory, for…

Over recent years, there has been a rapid development of deep learning (DL) in both industry and academia fields. However, finding the optimal hyperparameters of a DL model often needs high computational cost and human expertise. To…

We aim at capturing high-order statistics of feature vectors formed by a neural network, and propose end-to-end second- and higher-order pooling to form a tensor descriptor. Tensor descriptors require a robust similarity measure due to low…

Existing dense or paragraph video captioning approaches rely on holistic representations of videos, possibly coupled with learned object/action representations, to condition hierarchical language decoders. However, they fundamentally lack…

In the pursuit of developing expressive music performance models using artificial intelligence, this paper introduces DExter, a new approach leveraging diffusion probabilistic models to render Western classical piano performances. In this…

Learning from demonstration is a powerful method for teaching robots new skills, and having more demonstration data often improves policy learning. However, the high cost of collecting demonstration data is a significant bottleneck. Videos,…

Continual generalized category discovery has been introduced and studied in the literature as a method that aims to continuously discover and learn novel categories in incoming data batches while avoiding catastrophic forgetting of…

In practical recommendation scenarios, users often interact with items under multi-typed behaviors (e.g., click, add-to-cart, and purchase). Traditional collaborative filtering techniques typically assume that users only have a single type…

We present two deep learning approaches to narrative text understanding for character relationship modelling. The temporal evolution of these relations is described by dynamic word embeddings, that are designed to learn semantic changes…

In contrast to pedagogies like evidence-based teaching, personalized adaptive learning (PAL) distinguishes itself by closely monitoring the progress of individual students and tailoring the learning path to their unique knowledge and…

DenseNet architectures have demonstrated impressive performance in image classification tasks, but limited research has been conducted on using character-level DenseNet (char-DenseNet) architectures for text classification tasks. It is not…

Many Multi-Object Tracking (MOT) approaches exploit motion information to associate all the detected objects across frames. However, many methods that rely on filtering-based algorithms, such as the Kalman Filter, often work well in linear…

The ability to identify and temporally segment fine-grained human actions throughout a video is crucial for robotics, surveillance, education, and beyond. Typical approaches decouple this problem by first extracting local spatiotemporal…

Temporal hypergraphs provide a powerful paradigm for modeling time-dependent, higher-order interactions in complex systems. Representation learning for hypergraphs is essential for extracting patterns of the higher-order interactions that…

High accuracy video label prediction (classification) models are attributed to large scale data. These data could be frame feature sequences extracted by a pre-trained convolutional-neural-network, which promote the efficiency for creating…

Convolutional Neural Networks have demonstrated superior performance on single image depth estimation in recent years. These works usually use stacked spatial pooling or strided convolution to get high-level information which are common…

Differential evolution (DE) is a simple but powerful evolutionary algorithm, which has been widely and successfully used in various areas. In this paper, an event-triggered impulsive control scheme (ETI) is introduced to improve the…