52 accepted papers
Deep learning relies heavily on data augmentation to mitigate limited data, especially in medical imaging. Recent multimodal learning integrates text and images for segmentation, known as referring or text-guided image segmentation. However, common augmentations like rotation and flipping disrupt sp…
Improper exposure often leads to severe loss of details, color distortion, and reduced contrast. Exposure correction still faces two critical challenges: (1) the ignorance of object-wise regional semantic information causes the color shift artifacts; (2) real-world exposure images generally have no…
In retrieval-augmented generation, language models can generate incorrect responses if they fail to utilize query-relevant content from the retrieved evidence. This shifts the focus of uncertainty quantification (UQ) toward assessing contextual grounding, i.e., whether predictions are supported by q…
Multimodal Action Quality Assessment (AQA) has recently emerged as a promising paradigm. By leveraging complementary information across shared contextual cues, it enhances the discriminative evaluation of subtle intra-class variations in highly similar action sequences. However, partial modalities a
Scaling artist-designed meshes to high triangle numbers remains challenging for autoregressive generative models. Existing transformer-based methods suffer from long-sequence bottlenecks and limited quantization resolution, primarily due to the large number of tokens required and constrained quantiz
Segmenting 3D objects into parts is a long-standing challenge in computer vision. To overcome taxonomy constraints and generalize to unseen 3D objects, recent works turn to open-world part segmentation. These approaches typically transfer supervision from 2D foundation models, such as SAM, by liftin…
Large Vision-Language Models (LVLMs) encode visual inputs as dense sequences of patch-level tokens to capture fine-grained semantics. These visual tokens often outnumber their textual counterparts by a large margin, leading to substantial computational overhead and limiting the scalability of LVLMs
Classifying the status of NSCLC PD-L1 on chest CT is a cost-effective and non-invasive method. The existing multiple instance learning (MIL) methods are not effective for this task, due to the lack of an efficient feature encoder for 3D instances and ignoring the importance of representative instanc…
Long context large language models (LLMs) pose significant challenges for efficient serving due to the large memory footprint and high access overhead of KV cache.Retrieval-based KV cache reduction methods can mitigate these challenges, typically by offloading the complete KV cache to CPU and retrie…
Can Large Language Models (LLMs) simulate humans in making important decisions? Recent research has unveiled the potential of using LLMs to develop role-playing language agents (RPLAs), mimicking mainly the knowledge and tones of various characters. However, imitative decision-making necessitates a
Role-playing language agents (RPLAs) have emerged as promising applications of large language models (LLMs). However, simulating established characters presents a challenging task for RPLAs, due to the lack of authentic character datasets and nuanced evaluation methods using such data. In this paper…
As large language models (LLMs) grow more capable, they face increasingly diverse and complex tasks, making reliable evaluation challenging. The paradigm of LLMs as judges has emerged as a scalable solution, yet prior work primarily focuses on simple settings. Their reliability in complex tasks—wher
Stereo matching is a key technique for metric depth estimation in computer vision and robotics. Real-world challenges like occlusion and non-texture hinder accurate disparity estimation from binocular matching cues. Recently, monocular relative depth estimation has shown remarkable generalization us…
The fair and objective assessment of performances and competitions is a common pursuit and challenge in human society. The application of computer vision technology offers hope for this purpose, but it still faces obstacles such as occlusion and motion blur. To address these hindrances, our DanceFix…
Guided Depth Super-Resolution (GDSR) enhances low-resolution (LR) depth maps by leveraging high-resolution (HR) color images. The primary challenges involve achieving effective cross-modal data alignment and fusion, as well as incorporating multi-scale information within the Transformer architecture…
Prior research on training grounded factuality classification models to detect hallucinations in large language models (LLMs) has relied on public natural language inference (NLI) data and synthetic data. However, conventional NLI datasets are not well-suited for document-level reasoning, which is c…
Few-shot learning addresses the challenges of image classification with limited samples, but current methods often fail to fully utilize sample correlations and external semantic information, leading to low accuracy. To overcome these limitations, we propose a few-shot image classification method ba…
Recent advances in Large Language Model (LLM)-based Role-Playing Language Agents (RPLAs) have attracted broad attention in various applications. While chain-of-thought reasoning has shown importance in many tasks for LLMs, the internal thinking processes of RPLAs remain unexplored. Understanding cha
Long-term sports assessment is a challenging task in video understanding since it requires judging complex movement variations and action-music coordination. However, there is no direct correlation between the diverse background music and movements in sporting events. Previous works require a large…
Test-time adaptation (TTA) aims to adapt a source model to a target domain using only test data. Existing methods predominantly rely on unsupervised entropy minimization or its variants, which suffer from degeneration, leading to trivial solutions with low-entropy but inaccurate predictions. In this…
Self-supervised monocular depth estimation from RGB images has seen significant advancements recently, primarily because it eliminates the need for ground truth data during training. However, applying this technique to thermal images remains challenging due to their inherent characteristics, such as…
Spatial reasoning is a key capability in the field of artificial intelligence, especially crucial in areas such as robotics, computer vision, and natural language understanding. However, evaluating the ability of multimodal large language models (MLLMs) in complex spatial reasoning still faces chall…
Self-supervised depth estimation from videos involves predicting the depth map of a target frame and the pose changes between source and target frames. The reconstructed source frame is aligned with the target view using the predicted pose and depth information. Precise pose estimation significantly…
Conformal prediction yields a prediction set with guaranteed $1-\alpha$ coverage of the true target under the i.i.d. assumption, which can fail and lead to a gap between $1-\alpha$ and the actual coverage. Prior studies bound the gap using total variation distance, which cannot identify the gap cha…
Automatic anime sketch colorization aims to generate a color image from a sketch image, which is challenging due to limited structure and semantic understanding, leading to constrained style, and semantic color inconsistency. In this paper, we introduce a sketch to color diffusion model with semanti…
Role-playing agents (RPA) have been a popular application area for large language models (LLMs), attracting significant interest from both industry and academia. While existing RPAs well portray the characters’ knowledge and tones, they face challenges in capturing their minds, especially for small…
Large language models (LLMs) have demonstrated impressive performance and spurred numerous AI applications, in which role-playing agents (RPAs) are particularly popular, especially for fictional characters. The prerequisite for these RPAs lies in the capability of LLMs to understand characters from…
Role-playing agents (RPAs), powered by large language models, have emerged as a flourishing field of applications. However, a key challenge lies in assessing whether RPAs accurately reproduce the personas of target characters, namely their character fidelity. Existing methods mainly focus on the kno…
"Self-supervised representation learning on point cloud sequences is a challenging task due to the complex spatio-temporal structure. Most recent attempts aim to train the point cloud sequences representation model by reconstructing the point coordinates or designing frame-level contrastive learning…
Omnidirectional stereo matching (OSM) is an essential and reliable means for <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$360^{\circ }$</tex-math></inline-formula> depth sensing. However, following earlier works
"Action quality assessment (AQA) is a challenging vision task that requires discerning and quantifying subtle differences in actions from the same class. While recent research has made strides in creating fine-grained annotations for more precise analysis, existing methods primarily focus on coarse…
New Natural Langauge Process~(NLP) benchmarks are urgently needed to align with the rapid development of large language models (LLMs). We present Xiezhi, the most comprehensive evaluation suite designed to assess holistic domain knowledge.Xiezhi comprises multiple-choice questions across 516 diverse…
In this paper, we propose a novel embedded feature selection method, which is able to select the informative and discriminative features with the underlying submanifolds of data in intra-class being well preserved so as to improve the classification performance. Specifically, we first impose the l <…
Given a possibly false claim sentence, how can we automatically correct it with minimal editing? Existing methods either require a large number of pairs of false and corrected claims for supervised training or do not handle well errors spanning over multiple tokens within an utterance. In this paper…
Existing depth estimation methods infer scene depth only from stereo visible light (RGB) images. Since RGB imaging is sensitive to changes in light, it’s difficult to estimate depth information accurately in some degraded visibility conditions. In contrast, infrared (IR) imaging captures thermal rad…
In this paper, we propose a novel semi-supervised dimensionality reduction method based on local structured feature learning with dynamic maximum entropy graph. The proposed method first learns a local discriminative embedding subspace from labeled data for preserving the intrinsic sub-manifold stru…
In zero-shot cross-lingual event argument extraction(EAE) task, a model is typically trained on source language datasets and then applied on task language datasets. There is a trend to regard the zero-shot cross-lingual EAE task as a sequence generation task with manual prompts or discrete prompts.…
Sketch-based 3D shape retrieval is a challenging task due to the large domain discrepancy between sketches and 3D shapes. Since existing methods are trained and evaluated on the same categories, they cannot effectively recognize the categories that have not been used during training. In this paper,…
The ability to recognize analogies is fundamental to human cognition. Existing benchmarks to test word analogy do not reveal the underneath process of analogical reasoning of neural models. Holding the belief that models capable of reasoning should be right for the right reasons, we propose a first-…
Lexically constrained neural machine translation (NMT) draws much industrial attention for its practical usage in specific domains. However, current autoregressive approaches suffer from high latency. In this paper, we focus on non-autoregressive translation (NAT) for this problem for its efficiency…
Automatic segmentation of COVID-19 lesions is essential for computer-aided diagnosis. However, this task remains challenging because widely-used supervised based methods require large-scale annotated data that is difficult to obtain. Although an unsupervised method based on anomaly detection has sho…
Stereo matching has been widely used to estimate depth maps in terrestrial environments. However, it is difficult to achieve appealing performance in underwater environments, since adequate underwater stereo data with groundtruth depth information is not easily available for training an underwater d…
Existing color-guided depth super-resolution (DSR) approaches require paired RGB-D data as training examples where the RGB image is used as structural guidance to recover the degraded depth map due to their geometrical similarity. However, the paired data may be limited or expensive to be collected…
SinGAN shows impressive capability in learning internal patch distribution despite its limited effective receptive field. We are interested in knowing how such a translation-invariant convolutional generator could capture the global structure with just a spatially i.i.d. input. In this work, taking…
We develop a general approach to distill symbolic representations of a learned deep model by introducing strong inductive biases. We focus on Graph Neural Networks (GNNs). The technique works as follows: we first encourage sparse latent representations when we train a GNN in a supervised setting, th…
In this paper, we propose an effective point cloud generation method, which can generate multi-resolution point clouds of the same shape from a latent vector. Specifically, we develop a novel progressive deconvolution network with the learning-based bilateral interpolation. The learning-based bilate…
Precise segmentation of retinal vessels is crucial for a computer-aided diagnosis system of retinal fundus images. However, this task remains challenging due to large variations in scales and poor segmentation of capillary vessels. In this paper, we propose a semantics and multi-scale aggregation ne…
Deep network based methods have been proposed for accurate classification of pulmonary textures on CT images. However, such methods well-trained on CT data from one scanner cannot perform well when they are directly applied to the data from other scanners. This domain shift problem is caused by diff…
Recent advances in adversarial attacks uncover the intrinsic vulnerability of modern deep neural networks. Since then, extensive efforts have been devoted to enhancing the robustness of deep networks via specialized learning algorithms and loss functions. In this work, we take an architectural persp…
Feature upsampling is a key operation in a number of modern convolutional network architectures, e.g. feature pyramids. Its design is critical for dense prediction tasks such as object detection and semantic/instance segmentation. In this work, we propose Content-Aware ReAssembly of FEatures (CARAFE…
Video inpainting, which aims at filling in missing regions in a video, remains challenging due to the difficulty of preserving the precise spatial and temporal coherence of video contents. In this work we propose a novel flow-guided video inpainting approach. Rather than filling in the RGB pixels of…
Classification of pulmonary textures on CT images is essential for the development of a computer-aided diagnosis system of diffuse lung diseases. In this paper, we propose a novel method to classify pulmonary textures by using a deep neural network, which can make full use of appearance and geometry…