40 accepted papers
Recent research in Category-Agnostic Pose Estimation (CAPE) has adopted fixed textual keypoint description as semantic prior for two-stage pose matching frameworks. While this paradigm enhances robustness and flexibility by disentangling the dependency of support images, our critical analysis reveal
Understanding brain function represents a fundamental goal in neuroscience, with critical implications for therapeutic interventions and neural engineering applications. Computational modeling provides a quantitative framework for accelerating this understanding, but faces a fundamental trade-off be
Visual encoding and decoding models act as gateways to understanding the neural mechanisms underlying human visual perception. Typically, visual encoding models that predict brain activity from stimuli and decoding models that reproduce stimuli from brain activity are treated as distinct tasks, requ
Real-world data is rarely clean; it is plagued by severe class imbalance (long-tailed distributions) and label corruption. Current solutions lean heavily on ''black-box" meta-learning to re-weight samples. However, this paradigm introduces a fatal circular dependency: it relies on pristine, balanced…
To continuously enhance model adaptability in surgical video scene parsing, recent studies incrementally update it to progressively learn to segment an increasing number of surgical instruments over time. However, prior works constantly overlooked the potential of positive forward knowledge transfer
Recently, image-based 3D semantic occupancy prediction has become a hot topic in 3D scene understanding for autonomous driving. Compared with the bounding box form of 3D object detection, the ability to describe the fine-grained contours of any obstacles in the scene is the key insight of voxel occ…
Open-set fine-grained recognition (OSFGR) is the core exploration of building open-world intelligent systems. The challenge lies in the gradual semantic drift during the transition from coarse-grained to fine-grained categories. However, although existing methods leverage hierarchical representation…
Elucidating the functional mechanisms of the primary visual cortex (V1) remains a fundamental challenge in systems neuroscience. Current computational models face two critical limitations, namely the challenge of cross-modal integration between partial neural recordings and complex visual stimuli, a…
Individual brains exhibit striking structural and physiological heterogeneity, yet neural circuits can generate remarkably consistent functional properties across individuals, an apparent paradox in neuroscience. While recent studies have observed preserved neural representations in motor cortex thr…
Pairwise camera pose estimation from sparsely overlapping image pairs remains a critical and unsolved challenge in 3D vision. Most existing methods struggle with image pairs that have small or no overlap. Recent approaches attempt to address this by synthesizing intermediate frames using video inte…
Story generation stands as a crucial, yet formidable task, necessitating a profound grasp of subtle, often unspoken knowledge, along with context-specific cues to craft compelling narratives. The core challenges involve effectively harnessing this implicit knowledge and augmenting narrative diversit…
We present a Gaussian Splatting method for surface reconstruction using sparse input views. Previous methods relying on dense views struggle with extremely sparse Structure-from-Motion points for initialization. While learning-based Multi-view Stereo (MVS) provides dense 3D points, directly combinin…
Deciphering how visual stimuli are transformed into cortical responses is a fundamental challenge in computational neuroscience. This visual-to-neural mapping is inherently a one-to-many relationship, as identical visual inputs reliably evoke variable hemodynamic responses across trials, contexts, a…
With the rapid development of Large Language Models (LLMs), aligning these models with human preferences and values is critical to ensuring ethical and safe applications. However, existing alignment techniques such as RLHF or DPO often require direct fine-tuning on LLMs with billions of parameters,
With the increasing popularity of graph-based methods for dimensionality reduction and representation learning, node embedding functions have become important objects of study in the literature. In this paper, we take an axiomatic approach to understanding node embedding methods. Motivated by desira…
Traditional frame-based cameras inevitably suffer from non-uniform blur in real-world scenarios. Event cameras that record the intensity changes with high temporal resolution provide an effective solution for image deblurring. In this paper, we formulate the event-based image deblurring as an image…
Single image super-resolution (SISR), especially in the real world, usually builds a large amount of LR-HR image pairs to learn representations that contain rich textural and structural information. However, relying on massive data for model training not only reduces training efficiency, but also ca…
Recent studies have made remarkable progress in histopathology classification. Based on current successes, contemporary works proposed to further upgrade the model towards a more generalizable and robust direction through incrementally learning from the sequentially delivered domains. Unlike previou…
The Joint Detection and Embedding (JDE) framework has achieved remarkable progress for multiple object tracking. Existing methods often employ extracted embeddings to re-establish associations between new detections and previously disrupted tracks. However, the reliability of embeddings diminishes w…
Continuous normalizing flows (CNFs) learn an ordinary differential equation to transform prior samples into data. Flow matching (FM) has recently emerged as a simulation-free approach for training CNFs by regressing a velocity model towards the conditional velocity field. However, on constrained dom…
Understanding how biological visual systems process information is challenging because of the nonlinear relationship between visual input and neuronal responses. Artificial neural networks allow computational neuroscientists to create predictive models that connect biological and machine vision. Ma…
Mapping Low Dynamic Range (LDR) images with different exposures to High Dynamic Range (HDR) remains nontrivial and challenging on dynamic scenes due to ghosting caused by object motion or camera jitting. With the success of Deep Neural Networks (DNNs), several DNNs-based methods have been proposed t…
Deep learning (DL) based image super-resolution (SR) tech-niques have been well investigated for recent years. However, studies dedicated to SR image quality assessment (SR-IQA) have not been fully developed, which is even more difficult if pristine high-resolution (HR) images are lacking as a refer…
Semi-implicit variational inference (SIVI) has been introduced to expand the analytical variational families by defining expressive semi-implicit distributions in a hierarchical manner. However, the single-layer architecture commonly used in current SIVI methods can be insufficient when the target p…
Due to intensive human-robot interaction in exoskeletons, it is desirable to design and control the exoskeletons with behavior compatible to human limbs to achieve natural and energy-efficient motion assistance. This requires both novel variable stiffness actuators and also technologies able to dete
Multi-frame depth estimation generally achieves high accuracy relying on the multi-view geometric consistency. When applied in dynamic scenes, e.g., autonomous driving, this consistency is usually violated in the dynamic areas, leading to corrupted estimations. Many multi-frame methods handle dynami…
Generating a high-quality High Dynamic Range (HDR) image from dynamic scenes has recently been extensively studied by exploiting Deep Neural Networks (DNNs). Most DNNs-based methods require a large amount of training data with ground truth, requiring tedious and time-consuming work. Few-shot HDR ima…
Online time-optimal trajectory planning exists in a wide range of applications such as computer numerical control (CNC) manufacturing, robotics and autonomous vehicles. Generally, the methods to generate such time-parameterized trajectory can be categorized as offline methods and online methods. Off
In dynamic scenes, images often suffer from dynamic blur due to superposition of motions or low signal-noise ratio resulted from quick shutter speed when avoiding motions. Recovering sharp and clean result from the captured images heavily depends on the ability of restoration methods and the quality…
We propose a flexible framework for defining the 1-Laplacian of a hypergraph that incorporates edge-dependent vertex weights. These weights are able to reflect varying importance of vertices within a hyperedge, thus conferring the hypergraph model higher expressivity than homogeneous hypergraphs. We…
Optical flow estimation is a classical yet challenging task in computer vision. One of the essential factors in accurately predicting optical flow is to alleviate occlusions between frames. However, it is still a thorny problem for current top-performing optical flow estimation methods due to insuff…
The task space contouring performance is significant for the machining accuracy of industrial robotic manipulators, but the contouring control of end-effector which is important in the industry has received scant attention. In this letter, a novel task space contouring error estimation and control s
Modular robots have the potential for an unmatched ability to perform versatile and robust locomotion. However, designing effective and adaptive locomotion controllers for modular robots is challenging, resulting in a number of model-based methods that typically require various forms of prior knowle
A common challenge in personalized user preference prediction is the cold-start problem. Due to the lack of user-item interactions, directly learning from the new users' log data causes serious over-fitting problem. Recently, many existing studies regard the cold-start personalized preference predic…
Blind image quality assessment (BIQA) for authentically distorted images has always been a challenging problem, since images captured in the wild include varies contents and diverse types of distortions. The vast majority of prior BIQA methods focus on how to predict synthetic image quality, but fai…
Recently, context reasoning using image regions beyond local convolution has shown great potential for scene parsing. In this work, we explore how to incorperate the linguistic knowledge to promote context reasoning over image regions by proposing a Graph Interaction unit (GI unit) and a Semantic Co…
We consider a scenario where a robot is capable of autonomously opening previously unseen doors. Prior works either use model-based methods that rely strongly on accurate kinematic models, or learn a policy from scratch through trial-and-error, which cannot generalize to large variations in shape, a
We study the problem of jointly estimating several network processes that are driven by the same input, recasting it as one of blind identification of a bank of graph filters. More precisely, we consider the observation of several graph signals - i.e., signals defined on the nodes of a graph - and w…
We propose a single-image super-resolution method based on the gradient reconstruction. To predict the gradient field, we collect a dictionary of gradient patterns from an external set of images. We observe that there are patches representing singular primitive structures (e.g. a single edge), and n…
We study the problem of temporally consistent video post-processing. Previous post-processing algorithms usually either fail to keep high fidelity or fail to keep temporal consistency of output videos. In this paper, we observe experimentally that many image/video enhancement algorithms enforce a sp…