36 accepted papers
We study gradient-based data attribution, aiming to identify which training examples most influence a given output. Existing methods for this task either treat network parameters uniformly or rely on implicit weighting derived from Hessian approximations, which do not fully model functional heteroge…
People can view the same image differently: they focus on different regions, objects, and details in varying orders and describe them in distinct linguistic styles. This leads to substantial variability in image descriptions. However, existing models for personalized image description focus on lingu
Diffusion model (DM) based Video Super-Resolution (VSR) approaches achieve impressive perceptual quality. Diffusion model (DM) based Video Super-Resolution (VSR) approaches achieve impressive perceptual quality. However, existing DM-based VSR methods over-prioritize perceptual synthesis while neglec
Noise is an inevitable aspect of point cloud acquisition, necessitating filtering as a fundamental task within the realm of 3D vision. Existing learning-based filtering methods have shown promising capabilities on commonly used datasets. Nonetheless, the effectiveness of these methods is constrained…
Visual object counting is a fundamental computer vision task underpinning numerous real-world applications, from cell counting in biomedicine to traffic and wildlife monitoring. However, existing methods struggle to handle the challenge of stacked 3D objects in which most objects are hidden by those…
Weather prediction is a critical task for human society, where impressive progress has been made by training artificial intelligence weather prediction (AIWP) methods with reanalysis data. However, reliance on reanalysis data limits the AIWPs with shortcomings, including data assimilation biases an…
Understanding how humans would behave during hand-object interaction (HOI) is vital for applications in service robot manipulation and extended reality. To achieve this, some recent works simultaneously forecast hand trajectories and object affordances on human egocentric videos. The joint predictio
Text-to-image diffusion models have demonstrated remarkable capability in generating realistic images from arbitrary text prompts. However, they often produce inconsistent results for compositional prompts such as "two dogs" or "a penguin on the right of a bowl". Understanding these inconsistencies…
A personalized model for scanpath prediction provides insights into the visual preferences and attention patterns of individual subjects. However, existing methods for training scanpath prediction models are data-intensive and cannot be effectively personalized to new individuals with only a few ava…
Self-supervised learning of point cloud aims to leverage unlabeled 3D data to learn meaningful representations without reliance on manual annotations. However, current approaches face challenges such as limited data diversity and inadequate augmentation for effective feature learning. To address the…
Place recognition is a crucial component that enables autonomous vehicles to obtain localization results in GPS-denied environments. In recent years, multimodal place recognition methods have gained increasing attention. They overcome the weaknesses of unimodal sensor systems by leveraging complemen
Variation of Arctic sea ice has significant impacts on polar ecosystems, transporting routes, coastal communities, and global climate. Tracing the change of sea ice at a finer scale is paramount for both operational applications and scientific studies. Recent pan-Arctic sea ice forecasting methods t…
Token merging can effectively accelerate various vision systems by processing groups of similar tokens only once and sharing the results across them. However, existing token grouping methods are often ad hoc and random, disregarding the actual content of the samples. We show that preserving high-inf…
Forecasting how human hands would move around target objects on egocentric videos can provide prior knowledge to enhance the path planning capabilities of service robots and assistive wearable devices. During the hand-object interaction process, head movements always occur concurrently to provide ob
This paper presents a method that utilizes multiple camera views for the gaze target estimation (GTE) task. The approach integrates information from different camera views to improve accuracy and expand applicability, addressing limitations in existing single-view methods that face challenges such a…
Predicting hand motion is critical for understanding human intentions and bridging the action space between human movements and robot manipulations. Existing hand trajectory prediction (HTP) methods forecast the future hand waypoints in 3D space conditioned on past egocentric observations. However,
Arctic sea ice performs a vital role in global climate and has paramount impacts on both polar ecosystems and coastal communities. In the last few years, multiple deep learning based pan-Arctic sea ice concentration (SIC) forecasting methods have emerged and showcased superior performance over physi…
The task of occupancy forecasting (OCF) involves utilizing past and present perception data to predict future occupancy states of autonomous vehicle surrounding environments, which is critical for downstream tasks such as obstacle avoidance and path planning. Existing 3D OCF approaches struggle to p…
Understanding how the surrounding environment changes is crucial for performing downstream tasks safely and reliably in autonomous driving applications. Recent occupancy estimation techniques using only camera images as input can provide dense occupancy representations of large-scale scenes based on…
Fusion-based place recognition is an emerging technique jointly utilizing multi-modal perception data, to recognize previously visited places in GPS-denied scenarios for robots and autonomous vehicles. Recent fusion-based place recognition methods combine multi-modal features in implicit manners. Wh…
Place recognition is one of the most crucial modules for autonomous vehicles to identify places that were previously visited in GPS-invalid environments. Sensor fusion is considered an effective method to overcome the weaknesses of individual sensors. In recent years, multimodal place recognition fu
Learning unsigned distance fields (UDF) directly from raw point clouds as the implicit representation for surface reconstruction is a promising learning-based method for reconstructing open surfaces and supervision-free attributes. In most UDF methods, Chamfer Distance (CD), the commonly used metric…
We introduce algebraic machine reasoning, a new reasoning framework that is well-suited for abstract reasoning. Effectively, algebraic machine reasoning reduces the difficult process of novel problem-solving to routine algebraic computation. The fundamental algebraic objects of interest are the idea…
Two-stage object detectors generate object proposals and classify them to detect objects in images. These proposals often do not perfectly contain the objects but overlap with them in many possible ways, exhibiting great variability in the difficulty levels of the proposals. Training a robust classi…
Class-agnostic object counting aims to count object instances of an arbitrary class at test time. It is challenging but also enables many potential applications. Current methods require human-annotated exemplars as inputs which are often unavailable for novel categories, especially for autonomous sy…
Federated learning (FL) is a privacy-preserving distributed learning paradigm that enables clients to jointly train a global model. In real-world FL implementations, client data could have label noise, and different clients could have vastly different label noise levels. Although there exist methods…
Few-shot learning (FSL) aims to learn new categories with a few visual samples per class. Few-shot class representations are often biased due to data scarcity. To mitigate this issue, we propose to generate visual samples based on semantic embeddings using a conditional variational autoencoder (CVAE…
Data augmentation is an intuitive step towards solving the problem of few-shot classification. However, ensuring both discriminability and diversity in the augmented samples is challenging. To address this, we propose a feature disentanglement framework that allows us to augment features with random…
Analytic grasp planning algorithms typically approximate compliant contacts with soft point contact models to compute grasp quality, but these models are overly conservative and do not capture the full range of grasps available. While area contact models can reduce the number of false negatives pred…
Rapid and reliable robot bin picking is a critical challenge in automating warehouses, often measured in picks-per-hour (PPH). We explore increasing PPH using faster motions based on optimizing over a set of candidate grasps. The source of this set of grasps is two-fold: (1) grasp-analysis tools suc…
Robot grasping of deformable hollow objects such as plastic bottles and cups is challenging, as the grasp should resist disturbances while minimally deforming the object so as not to damage it or dislodge liquids. We propose minimal work as a novel grasp quality metric that combines wrench resistanc…
We consider the face recognition task where facial images of the same identity (person) is expected to be closer in the representation space, while different identities be far apart. Several recent studies encourage the intra-class compactness by developing loss functions that penalize the variance…
The acceptance of teleoperation applications like tele-driving, tele-surgery, tele-maintenance, etc., is challenged by the quality-reducing effect of end-to-end latency. Particularly, when users wear Head-Mounted Displays to enhance the immersive experience, the lag between head motion and display r…
This paper develops a novel methodology for using symbolic knowledge in deep learning. From first principles, we derive a semantic loss function that bridges between neural output vectors and logical constraints. This loss function captures how close the neural network is to satisfying the constrain…
Assessing grasp stability is essential to prevent the failure of robotic manipulation tasks due to sensory data and object uncertainties. Learning-based approaches are widely deployed to infer the success of a grasp. Typically, the underlying model used to estimate the grasp stability is trained for…
We present a friction model for the curved contact area between a deformable object and soft parallel gripper jaws for grasping posture estimation. We show that the assumption of a planar contact area leads to an overestimation of the frictional force and torque, which might cause the object to slip…