42 accepted papers
The field of 360-degree omnidirectional understanding has been receiving increasing attention for advancing spatial intelligence. However, the lack of large-scale and diverse data remains a major limitation. In this work, we propose AirSim360, a simulation platform for omnidirectional data from aeri
Recent advances in 3D Gaussian Splatting (3DGS) enable real-time, high-fidelity novel view synthesis (NVS) with explicit 3D representations. However, performance degradation and instability remain significant under sparse-view conditions. In this work, we identify two key failure modes under sparse-…
Panorama has a full FoV (360$^\circ\times$180$^\circ$), offering a more complete visual description than perspective images. Thanks to this characteristic, panoramic depth estimation is gaining increasing traction in 3D vision. However, due to the scarcity of panoramic data, previous methods are oft…
In this work, we present a panoramic metric depth foundation model that generalizes across diverse scene distances. We explore a data-in-the-loop paradigm from the view of both data construction and framework design. We collect a large-scale dataset by combining public datasets, high-quality synthet
The emergence of foundation models has substantially advanced zero-shot generalization in monocular depth estimation (MDE), as exemplified by the Depth Anything series. However, given access to some data from downstream tasks, a natural question arises: can the performance of these models be further
Posts containing multiple images have significant research potential in Multimodal Named Entity Recognition nowadays. The previous methods determine whether the images are related to named entities in the text through similarity computation, such as using CLIP. However, it is not effective in some c…
Empathetic response generation is a significant domain in Natural Language Processing (NLP). Its development is a critical step toward achieving humanized AI systems. However, current evaluations of empathetic dialogue models are primarily single-turn and static, leading to bias between evaluation r…
Complex chart understanding tasks demand advanced visual recognition and reasoning capabilities from multimodal large language models (MLLMs). However, current research provides limited coverage of complex chart scenarios and computation-intensive reasoning tasks prevalent in real-world applications
Multimodal Large Language Models (MLLMs) bridge the gap between visual and textual data, enabling a range of advanced applications. However, complex internal interactions among visual elements and their alignment with text can introduce vulnerabilities, which may be exploited to bypass safety mechan…
Complex question answering (QA) is a challenging task in artificial intelligence research which requires reasoning based on related knowledge. The retrieval-augmented generation (RAG) based on large language models (LLMs) have become one promising solution in QA. To facilitate RAG more effectively,…
Automatically generating high-quality mathematical problems that align with educational objectives is a crucial task in NLP-based educational technology. Traditional generation methods focus primarily on textual quality, but they often overlook educational objectives. Moreover, these methods address…
3D Gaussian Splatting (3DGS) has shown promising results for Novel View Synthesis. However, while it is quite effective when based on high-quality images, its performance declines as image quality degrades, due to lack of resolution, motion blur, noise, compression artifacts, or other factors common…
Robust Federated Graph Learning (FGL) provides an effective decentralized framework for training Graph Neural Networks (GNNs) in noisy-label environments. However, the subtlety of noise during training presents formidable obstacles for developing robust FGL systems. Previous robust FL approaches nei…
The goal of open relation extraction (OpenRE) is to develop an RE model that can generalize to new relations not encountered during training. Existing studies primarily formulate OpenRE as a clustering task. They first cluster all test instances based on the similarity between the instances, and the
While recent low-cost radar-camera approaches have shown promising results in multi-modal 3D object detection, both sensors face challenges from environmen- tal and intrinsic disturbances. Poor lighting or adverse weather conditions de- grade camera performance, while radar suffers from noise and po…
Open-source Large Language Models (LLMs) often employ safety alignment methods to resist harmful instructions. However, recent research shows that maliciously fine-tuning these LLMs on harmful data can easily bypass these safeguards. To counter this, we theoretically uncover why malicious fine-tunin…
Recent open-vocabulary human-object interaction (OV-HOI) detection methods primarily rely on large language model (LLM) for generating auxiliary descriptions and leverage knowledge distilled from CLIP to detect unseen interaction categories. Despite their effectiveness, these methods face two challe…
As a foundational component of cognitive intelligence, theory of mind (ToM) can make AI more closely resemble human thought processes, thereby enhancing their interaction and collaboration with human. In particular, it can significantly improve a model's comprehension of videos in complex scenes. Ho…
In this paper, we introduce DeAR (_Decompose-Analyze-Rethink_), a framework that iteratively builds a reasoning tree to tackle intricate problems within a single large language model (LLM). Unlike approaches that extend or search for rationales, DeAR is featured by 1) adopting a tree-based question…
Domain adaptation from labeled source domains to the target domain is important in practical summarization scenarios. However, the key challenge is domain knowledge disentanglement. In this work, we explore how to disentangle domain-invariant knowledge from source domains while learning specific kno…
Recently, multimodal named entity recognition (MNER) has emerged as a vital research area within named entity recognition. However, current MNER datasets and methods are predominantly based on text and a single accompanying image, leaving a significant research gap in MNER scenarios involving multip…
"All-in-one image restoration aims to handle multiple degradation types using one model. This paper proposes a simple pipeline for all-in-one blind image restoration to Restore Anything with Masks (). We focus on the image content by utilizing Mask Image Modeling to extract intrinsic image informati…
Dynamic scene graph generation (SGG) focuses on detecting objects in a video and determining their pairwise relationships. Existing dynamic SGG methods usually suffer from several issues, including 1) Contextual noise, as some frames might contain occluded and blurred objects. 2) Label bias, primari…
Endowing dialogue agents with personas is the key to delivering more human-like conversations. However, existing persona-grounded dialogue systems still lack informative details of human conversations and tend to reply with inconsistent and generic responses. One of the main underlying causes is tha…
For AR applications, the present monocular VO methods can be further improved to provide more real-time and accurate self-localization in a dynamic environment with motion disturbance. This letter proposes the CCVO (Cascaded CNNs for Visual Odometry) which is a monocular VO approach to realize end-t
Visual grounding is a crucial multi-modal job for locating the objects that the referring queries refer to in images. In recent years, both fully-supervised and weakly-supervised algorithms rely on a large number of query annotations. However, collecting queries in natural language is labor-intensiv…
Understanding mathematical questions effectively is a crucial task, which can benefit many applications, such as difficulty estimation. Researchers have drawn much attention to designing pre-training models for question representations due to the scarcity of human annotations (e.g., labeling difficu…
Deep learning methods have shown remarkable performance in image denoising, particularly when trained on large-scale paired datasets. However, acquiring such paired datasets for real-world scenarios poses a significant challenge. Although unsupervised approaches based on generative adversarial netwo…
Visual question answering (VQA) is a fundamental and challenging cross-modal task. This task requires the model to fully understand the image’s content and reason out the answer based on the question. Existing VQA models understand visual content mainly based on bottom-up or grid features. However,…
Succinctly summarizing dialogue is a task of growing interest, but inherent challenges, such as insufficient training data and low information density impede our ability to train abstractive models. In this work, we propose a novel curriculum-based prompt learning method with self-training to addres…
Scene graph generation (SGG) aims to detect objects and predict their pairwise relationships within an image. Current SGG methods typically utilize graph neural networks (GNNs) to acquire context information between objects/relationships. Despite their effectiveness, however, current SGG methods onl…
Scene graph generation (SGG) aims to detect objects and predict the relationships between each pair of objects. Existing SGG methods usually suffer from several issues, including 1) ambiguous object representations, as graph neural network-based message passing (GMP) modules are typically sensitive…
Visual grounding focuses on establishing fine-grained alignment between vision and natural language, which has essential applications in multimodal reasoning systems. Existing methods use pre-trained query-agnostic visual backbones to extract visual feature maps independently without considering the…
Few-shot learning can recognize a novel category based on only a few samples because it learns to learn from a lot of labeled samples during the training process. When data is insufficient, the performance is affected. And it is expensive to obtain a large-scale finegrained dataset with annotation.…
Automatically solving math word problems is a crucial task for exploring the intelligence levels of machines in the general AI domain. It is highly challenging since it requires not only natural language understanding but also mathematical expression inference. Existing solutions usually explore seq…
Few-shot learning task aims to explore a model that is able to quickly learn new concepts by learning a few examples. The current approaches learning new categories with few images or even a single image are only based on the the visual modality. However, it is difficult to learn the representative…
Building a good feature space is essential for the metric-based few-shot algorithms to recognize a novel class with only a few samples. The feature space is often built by Convolutional Neural Networks (CNNs). However, CNNs primarily focus on local information with the limited receptive field, and t…
During COVID-19, with a heavy sprayer filled with disinfectant, the risk of infection for epidemic prevention personnel has been increased by long-term environmental disinfection. In order to reduce the burden and save energy of human, this letter proposed a Wheel-Legged Robotic Limb (WRL) for the c
Scene graph generation (SGG) aims to detect objects in an image along with their pairwise relationships. There are three key properties of scene graph that have been underexplored in recent works: namely, the edge direction information, the difference in priority between nodes, and the long-tailed d…
Multiple Sequence Alignment and Motif Discovery, known as NP-hard problems, are two fundamental tasks in Bioinformatics. Existing approaches to these two problems are based on either local search methods such as Expectation Maximization (EM), Gibbs Sampling or greedy heuristic methods. In this work,…
In this paper, parameter estimation for multi-dimensional sinusoids in additive impulsive noise is addressed. Our underlying idea is to minimize the ℓ <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</sub> -norm of the residual error tensor, where 1 <;…
MAD-Bayes (MAP-based Asymptotic Derivations) has been recently proposed as a general technique to derive scalable algorithm for Bayesian Nonparametric models. However, the combinatorial nature of objective functions derived from MAD-Bayes results in hard optimization problem, for which current pract…