Related papers: TreeSBA: Tree-Transformer for Self-Supervised Sequ…

Several classification methods assume that the underlying distributions follow tree-structured graphical models. Indeed, trees capture statistical dependencies between pairs of variables, which may be crucial to attain low classification…

Pre-training is a strong strategy for enhancing visual models to efficiently train them with a limited number of labeled images. In semantic segmentation, creating annotation masks requires an intensive amount of labor and time, and…

Visual perception tasks often require vast amounts of labelled data, including 3D poses and image space segmentation masks. The process of creating such training data sets can prove difficult or time-intensive to scale up to efficacy for…

Supervised deep learning methods for segmentation require large amounts of labelled training data, without which they are prone to overfitting, not generalizing well to unseen images. In practice, obtaining a large number of annotations…

Recent advances in reinforcement learning (RL) have significantly enhanced the agentic capabilities of large language models (LLMs). In long-term and multi-turn agent tasks, existing approaches driven solely by outcome rewards often suffer…

Despite the success of fully-supervised human skeleton sequence modeling, utilizing self-supervised pre-training for skeleton sequence representation learning has been an active field because acquiring task-specific skeleton annotations at…

In this work, we present a transformer-based framework for predicting future pedestrian states based on clustered historical trajectory data. In previous studies, researchers propose enhancing pedestrian trajectory predictions by using…

Randomly masking and predicting word tokens has been a successful approach in pre-training language models for a variety of downstream tasks. In this work, we observe that the same idea also applies naturally to sequential decision making,…

This paper investigates an under-explored but important problem: given a collection of pre-trained neural networks, predicting their performance on each multi-modal task without fine-tuning them, such as image recognition, referring,…

Since the preparation of labeled data for training semantic segmentation networks of point clouds is a time-consuming process, weakly supervised approaches have been introduced to learn from only a small fraction of data. These methods are…

Tree perception is an essential building block toward autonomous forestry operations. Current developments generally consider input data from lidar sensors to solve forest navigation, tree detection and diameter estimation problems. Whereas…

It is desirable to enable robots capable of automatic assembly. Structural understanding of object parts plays a crucial role in this task yet remains relatively unexplored. In this paper, we focus on the setting of furniture assembly from…

Label-supervised manifold alignment bridges the gap between unsupervised and correspondence-based paradigms by leveraging shared label information to align multimodal datasets. Still, most existing methods rely on Euclidean geometry to…

Many advanced Learning from Demonstration (LfD) methods consider the decomposition of complex, real-world tasks into simpler sub-tasks. By reusing the corresponding sub-policies within and between tasks, they provide training data for each…

Individual tree segmentation (ITS) from LiDAR point clouds is fundamental for applications such as forest inventory, carbon monitoring and biodiversity assessment. Traditionally, ITS has been achieved with unsupervised geometry-based…

We propose to compose dynamic tree structures that place the objects in an image into a visual context, helping visual reasoning tasks such as scene graph generation and visual Q&A. Our visual context tree model, dubbed VCTree, has two key…

With the propagation of sensor devices applied in smart home, activity recognition has ignited huge interest and most existing works assume that there is only one habitant. While in reality, there are generally multiple residents at home,…

In a setting where segmentation models have to be built for multiple datasets, each with its own corresponding label set, a straightforward way is to learn one model for every dataset and its labels. Alternatively, multi-task architectures…

Text generation is a fundamental building block in natural language processing tasks. Existing sequential models performs autoregression directly over the text sequence and have difficulty generating long sentences of complex structures.…

Vision-Language-Action (VLA) models have recently emerged, demonstrating strong generalization in robotic scene understanding and manipulation. However, when confronted with long-horizon tasks that require defined goal states, such as LEGO…