Related papers: Constructing Object Groups Corresponding to Concep…

Reliably predicting human intent in hand-object interactions is an open challenge for computer vision. Our research concentrates on a fundamental sub-problem: the fine-grained classification of atomic interaction states, namely…

Many prediction problems across science and engineering, especially in finance and economics, involve large cross-sections of individual time series, where each unit (e.g., a loan, stock, or customer) is driven by unit-level features and…

We investigate the use of sequence analysis for behavior modeling, emphasizing that sequential context often outweighs the value of aggregate features in understanding human behavior. We discuss framing common problems in fields like…

In this paper, we focus on unsupervised representation learning for skeleton-based action recognition. Existing approaches usually learn action representations by sequential prediction but they suffer from the inability to fully learn…

Multiresponse data with complex group structures in both responses and predictors arises in many fields, yet, due to the difficulty in identifying complex group structures, only a few methods have been studied on this problem. We propose a…

Region based object detectors achieve the state-of-the-art performance, but few consider to model the relation of proposals. In this paper, we explore the idea of modeling the relationships among the proposals for object detection from the…

Meetings typically involve multiple participants and lengthy conversations, resulting in redundant and trivial content. To overcome these challenges, we propose a two-step framework, Reconstruct before Summarize (RbS), for effective and…

Source code summarizing is a task of writing short, natural language descriptions of source code behavior during run time. Such summaries are extremely useful for software development and maintenance but are expensive to manually…

A powerful data transformation method named guided projections is proposed creating new possibilities to reveal the group structure of high-dimensional data in the presence of noise variables. Utilising projections onto a space spanned by a…

Contrastive learning models have achieved great success in unsupervised visual representation learning, which maximize the similarities between feature representations of different views of the same image, while minimize the similarities…

Most existing video moment retrieval methods rely on temporal sequences of frame- or clip-level features that primarily encode global visual and semantic information. However, such representations often fail to capture fine-grained object…

The tracking-by-detection framework requires a set of positive and negative training samples to learn robust tracking models for precise localization of target objects. However, existing tracking models mostly treat different samples…

A fundamental challenge in graph mining is the ever-increasing size of datasets. Graph summarization aims to find a compact representation resulting in faster algorithms and reduced storage needs. The flip side of graph summarization is the…

Several learning applications require solving high-dimensional regression problems where the relevant features belong to a small number of (overlapping) groups. For very large datasets and under standard sparsity constraints, hard…

We show that numerical quasi-one-dimensional renormalization group allows accurate study of weakly coupled chains with modest computational effort. We perform a systematic comparison with exact diagonalization results in two and three-leg…

We describe SynGraphy, a method for visually summarising the structure of large network datasets that works by drawing smaller graphs generated to have similar structural properties to the input graphs. Visualising complex networks is…

We propose a framework to continuously learn object-centric representations for visual learning and understanding. Existing object-centric representations either rely on supervisions that individualize objects in the scene, or perform…

Trajectory planning in robotics is understood as generating a sequence of joint configurations that will lead a robotic agent, or its manipulator, from an initial state to the desired final state, thus completing a manipulation task while…

Learning graphical causal structures from time series data presents significant challenges, especially when the measurement frequency does not match the causal timescale of the system. This often leads to a set of equally possible…

The recovery of types from stripped binaries is a key to exact decompilation, yet its practical realization suffers. For composite structures in particular, both layout and semantic fidelity are required to enable end-to-end reconstruction.…