90 accepted papers
Spiking Neural Networks (SNNs) become popular due to excellent energy efficiency, yet facing challenges for effective model training. Recent works improve this by introducing knowledge distillation (KD) techniques, with the pre-trained artificial neural networks (ANNs) used as teachers and the targe
3D visual grounding encompassing 3D referring expression comprehension (3DREC) and segmentation (3DRES) requires robust cross-modal representation to achieve fine-grained semantic alignment and precise geometric reasoning. However, most methods employ unimodal pre-trained encoders that transfer visu…
Medical image segmentation supports clinical workflows by precisely delineating anatomical structures and lesions. However, medical image datasets medical image datasets suffer from acquisition noise and annotation ambiguity, causing pervasive data uncertainty that substantially undermines model rob
Diffusion policies for visuomotor robot manipulation tasks achieve remarkable dexterity and robustness while only training on a small number of task demonstrations. However, the reason for this performance remains a mystery. In this paper, we offer a surprising hypothesis: diffusion policies essent…
Diffusion models have demonstrated remarkable success in image and video generation, yet their practical deployment remains hindered by the substantial computational overhead of multi-step iterative sampling. Among acceleration strategies, caching-based methods offer a training-free and effective so
Semantic understanding of large-scale aerial scenes represents a critical challenge in 3D computer vision, hindered by the prohibitive cost of dense annotation. This paper introduces EvoPropGS, a novel approach for the semantic segmentation of 3D Gaussian Splatting models that requires only minimal
Current AAV autonomous flights exhibit efficient performance in both indoor and field environments. However, they often face significant challenges in large-scale and cluttered environments, where the vast amount of captured data can lead to computation and storage bottlenecks. Additionally, the existin…
Real-time satellite video tracking poses distinct challenges, including accommodating high spatial-temporal resolution, dynamic backgrounds, and constrained onboard computational resources. While Discriminative Correlation Filter (DCF)-based methods offer high-speed inference, they suffer from limit…
In recent years, the rapid progress of deep learning has driven notable advancements in satellite video tracking, a critical task for applications such as environmental monitoring, disaster management, and defense. Despite these strides, existing approaches remain constrained by their inability to h
Vision-Language Navigation (VLN) enables agents to navigate in complex environments by following natural language instructions grounded in visual observations. Although most existing work has focused on ground-based robots or outdoor Unmanned Aerial Vehicles (UAVs), indoor UAV-based VLN remains unde
Recently, Interleaved-modal Chain-of-Thought (ICoT) reasoning has achieved remarkable success by leveraging both multimodal inputs and outputs, attracting increasing attention. While achieving promising performance, current ICoT methods still suffer from two major limitations: (1) Static Visual Thou
Referring expression comprehension and segmentation (RECS) task plays a vital role in remote sensing due to its high efficiency in multi-tasking. However, RECS has reached a performance bottleneck rooted in representational insufficiency, primarily due to cross-task representational fragmentation in
Offline-to-online reinforcement learning harnesses the stability of offline pretraining and the flexibility of online fine-tuning. A key challenge lies in the non-stationary distribution shift between offline datasets and the evolving online policy. Common approaches often rely on static mixing rati
Open-Vocabulary Object Detection (OVOD) shows promise in remote sensing (RS), but due to its unique value, there are challenges such as the predominance of background regions, sparse labels, limited semantic information, and difficulties in semi-supervised training. To tackle these challenges, we pr
Large language models (LLMs) suffer from hallucination and context forgetting. Prior studies suggest that attention drift is a primary cause of these problems, where LLMs' focus shifts towards newly generated tokens and away from the initial input context. To address this, we make use of a related,…
Text-driven 3D editing, enabled by advancements in 3D reconstruction techniques such as NeRF and 3D Gaussian Splatting, aims to provide intuitive scene customization. However, existing methods frequently exhibit limitations in controllability and consistency. To address these shortcomings, we propos
In the domain of merchant-oriented risk control decisions within e-commerce, balancing the effectiveness of risk management with merchant satisfaction remains a critical challenge. Strict risk control strategies, while effectively mitigating risks, often lead to increased merchant dissatisfaction. C…
Integrating frames and events has become a widely accepted solution for various tasks in challenging scenarios. However, most multimodal methods directly convert events into image-like formats synchronized with frames and process each stream through separate two-branch backbones, making it difficult…
Chain-of-Thought (CoT) has been a widely adopted prompting method, eliciting impressive reasoning abilities of Large Language Models (LLMs). Inspired by the sequential thought structure of CoT, a number of Chain-of-X (CoX) methods have been developed to address challenges across diverse domains and…
Gait sequences exhibit sequential structures and contextual relationships similar to those in natural language, where each element--whether a word or a gait step--is connected to its predecessors and successors. This similarity enables the transformation of gait sequences into "texts" containing ide…
Investigating hallucination issues in large language models (LLMs) within cross-lingual and cross-modal scenarios can greatly advance the large-scale deployment in real-world applications. Nevertheless, the current studies are limited to a single scenario, either cross-lingual or cross-modal, leavin…
Domain generalization in 3D segmentation is a critical challenge in deploying models to unseen environments. Current methods mitigate the domain shift by augmenting the data distribution of point clouds. However, the model learns global geometric patterns in point clouds while ignoring the category-…
Current UAV autonomous flights exhibit efficient performance in both indoor and field environments. However, they often face significant challenges in large-scale and cluttered environments, where the vast amount of captured data can lead to computation and storage bottlenecks. Additionally, the exi
Facial attractiveness prediction (FAP) has long been an important computer vision task, which could be widely applied in live videos with facial retouching. However, previous FAP datasets are either small or closed-source. Moreover, the corresponding FAP models exhibit limited generalization and ada…
Accurately modeling complex dynamic spatio-temporal systems requires capturing flow-mediated interdependencies and context-sensitive interaction dynamics. Existing methods, predominantly graph-based or attention-driven, rely on similarity-driven connectivity assumptions, neglecting asymmetric flow e…
Motion forecasting for on-road traffic agents presents both a significant challenge and a critical necessity for ensuring safety in autonomous driving systems. In contrast to most existing data-driven approaches that directly predict future trajectories, we rethink this task from a planning perspect…
With the growing adoption of large language models (LLMs) in NLP tasks, concerns about their fairness have intensified. Yet, most existing fairness benchmarks rely on closed-ended evaluation formats, which diverge from real-world open-ended interactions. These formats are prone to position bias and
Modality exploration has been repeatedly mentioned in gait recognition, evolving from silhouette to parsing, mesh, point clouds, etc. These latest modalities agree that silhouette is less affected by background and clothing noises, but argue it loses too much valuable discriminative information. The…
Vision-language models like CLIP have demonstrated strong zero-shot generalization, making them valuable for various downstream tasks through prompt learning. However, existing test-time prompt tuning methods, such as entropy minimization, treat both text and visual prompts as fixed learnable parame…
Point-of-Interest (POI) recommendation has become increasingly important in the trajectory prediction domain. However, most existing approaches focus on a single scale and tend to overemphasize either spatial or temporal aspects. These methods often overlook the temporal dependencies in movement beh…
Visual grounding (VG) refers to detecting the specific objects in images based on linguistic expressions, and it has profound significance in the advanced interpretation of natural images. In remote sensing image interpretation, visual grounding is limited by characteristics such as the complex scen
We present Latent Theory of Mind (LatentToM), a decentralized diffusion policy architecture for collaborative robot manipulation. Our policy allows multiple manipulators with their own perception and computation to collaborate with each other towards a common task goal with or without explicit commu…
With its powerful visual-language alignment capability, CLIP performs well in zero-shot and few-shot learning tasks. However, we found in experiments that CLIP's logits suffer from serious inter-class confusion problems in downstream tasks, and the ambiguity between categories seriously affects the…
As large language models (LLMs) are increasingly applied to various NLP tasks, their inherent biases are gradually disclosed. Therefore, measuring biases in LLMs is crucial to mitigate its ethical risks. However, most existing bias evaluation datasets are focus on English andNorth American culture,…
Achieving effective unified pretraining on large time series corpora remains an open challenge in developing time series foundation models. Existing methods, such as Moirai, introduce multiple projection layers for time series of different frequencies to account for high data heterogeneity. We ident…
Attribute-Missing Graph Clustering addresses the challenging problem of incomplete node attribute information in graphs. Recent advancements in self-supervised learning techniques, particularly contrastive learning and generative approaches, have shown effectiveness in tackling tasks involving missi…
Offline-to-online Reinforcement Learning (O2O RL) aims to perform online fine-tuning on an offline pre-trained policy to minimize costly online interactions. Existing work used offline datasets to generate data that conform to the online data distribution for data augmentation. However, generated da…
Reinforcement learning (RL) has shown remarkable success in training agents to achieve high-performing policies, particularly in domains like Game AI where simulation environments enable efficient interactions. However, despite their success in maximizing these returns, such online-trained policies…
What is a gait? Appearance-based gait networks consider a gait as the human shape and motion information from images. Model-based gait networks treat a gait as the human inherent structure from points. However, the considerations remain vague for humans to comprehend truly. In this work, we introduc…
In this letter, we address the problem of exploration and metric-semantic mapping of multi-floor GPS-denied indoor environments using Size Weight and Power (SWaP) constrained aerial robots. Most previous work in exploration assumes that robot localization is solved. However, neglecting the state unc
Spiking Transformers have gained considerable attention because they achieve both the energy efficiency of Spiking Neural Networks (SNNs) and the high capacity of Transformers. However, the existing Spiking Transformer architectures, derived from Artificial Neural Networks (ANNs), exhibit a notable…
The utilization of Large Language Models (LLMs) in financial trading has primarily been concentrated within the stock market, aiding in economic and financial decisions. Yet, the unique opportunities presented by the cryptocurrency market, noted for its on-chain data’s transparency and the critical…
"Recent pose-based gait recognition methods, which utilize human skeletons as the model input, have demonstrated significant potential in handling variations in clothing and occlusions. However, methods relying on such skeleton to encode pose are constrained mainly by two problems: (1) poor performa…
"Gait recognition is to seek correct matches for query individuals by their unique walking patterns. However, current methods focus solely on extracting individual-specific features, overlooking “interpersonal” relationships. In this paper, we propose a novel Relation Descriptor that captures not on…
Large Language Models (LLMs) have shown propensity to generate hallucinated outputs, i.e., texts that are factually incorrect or unsupported. Existing methods for alleviating hallucinations typically require costly human annotations to identify and correct hallucinations in LLM outputs. Moreover, mo…
Reasoning is a fundamental ability towards artificial general intelligence (AGI). Fueled by the success of deep learning, the neural logic machines models (NLMs) have introduced novel neural-symbolic structures and demonstrate great performance and generalization on reasoning and decision-making tas…
Neural Radiance Fields (NeRF) have been successfully applied in various aerial scenes yet they face challenges with sparse views due to limited supervision. The acquisition of dense aerial views is often prohibitive as unmanned aerial vehicles (UAVs) may encounter constraints in perspective range an…
"Extensive occlusions in real-world scenarios pose challenges to gait recognition due to missing and noisy information, as well as body misalignment in position and scale. We argue that rich dynamic contextual information within a gait sequence inherently possesses occlusion-solving traits: 1) Adjac…
Code comments are crucial for gaining in-depth insights to facilitate code comprehension. The key to obtaining these insights lies in precisely summarizing the main purpose of the code. Recent approaches on code comment generation lie in prompting large language models (LLMs) such as ChatGPT, instea…
Gait recognition is a promising biometric method that aims to identify pedestrians from their unique walking patterns. Silhouette modality, renowned for its easy acquisition, simple structure, sparse representation, and convenient modeling, has been widely employed in controlled in-the-lab research.…
Speech enhancement seeks to extract clean speech from noisy signals. Traditional deep learning methods face two challenges: efficiently using information in long speech sequences and high computational costs. To address these, we introduce the Spiking Structured State Space Model (SpikingS4). This a…
Unlike natural language processing and computer vision, the development of Foundation Models (FMs) for time series forecasting is blocked due to data scarcity. While recent efforts are focused on building such FMs by unlocking the potential of language models (LMs) for time series analysis, dedicat…
Data collection for forestry, timber, and agriculture relies on manual techniques which are labor-intensive and time-consuming. We seek to demonstrate that robotics offers improvements over these techniques and can accelerate agricultural research, beginning with semantic segmentation and diameter e…
Pre-trained vision-language(V-L) models such as CLIP have demonstrated impressive Zero-Shot performance in many downstream tasks. Since adopting contrastive video-text pairs methods like CLIP to video tasks is limited by its high cost and scale, recent approaches focus on efficiently transferring th…
Accurate and robust state estimation is critical for autonomous navigation of robot teams. This task is especially challenging for large groups of size, weight, and power (SWAP) constrained aerial robots operating in perceptually-degraded GPS-denied environments. We can, however, actively increase t…
Traditional approaches for active mapping focus on building geometric maps. For most real-world applications, however, actionable information is related to semantically meaningful objects in the environment. We propose an approach to the active metric-semantic mapping problem that enables multiple h…
The target of person re-identification (ReID) and gait recognition is consistent, that is to match the target pedestrian under surveillance cameras. For the cloth-changing problem, video-based ReID is rarely studied due to the lack of a suitable cloth-changing benchmark, and gait recognition is ofte…
Unmanned aerial vehicles (UAVs) must fly at low altitudes to execute certain missions when operating in complex mountainous areas. However, in these environments, UAVs lose their line-of-sight (LOS) communication with the ground station (GS) due to the obstruction of the mountains and are unable to
Linking computational natural language processing (NLP) models and neural responses to language in the human brain on the one hand facilitates the effort towards disentangling the neural representations underpinning language perception, on the other hand provides neurolinguistics evidence to evaluat…
To address the challenges of long-tailed classification, researchers have proposed several approaches to reduce model bias, most of which assume that classes with few samples are weak classes. However, recent studies have shown that tail classes are not always hard to learn, and model bias has been…
Spatio-Temporal Graph (STG) forecasting is a fundamental task in many real-world applications. Spatio-Temporal Graph Neural Networks have emerged as the most popular method for STG forecasting, but they often struggle with temporal out-of-distribution (OoD) issues and dynamic spatial causation. In t…
Model bias triggered by long-tailed data has been widely studied. However, measure based on the number of samples cannot explicate three phenomena simultaneously: (1) Given enough data, the classification performance gain is marginal with additional samples. (2) Classification performance decays pre…
The Wav2Vec and its variants have achieved unprecedented success in computational auditory and speech processing. Meanwhile, neural encoding studies that integrate the superb representation capability of Wav2Vec and link those representations to brain activities have provided novel insights into a f…
Road traffic forecasting plays a critical role in smart city initiatives and has experienced significant advancements thanks to the power of deep learning in capturing non-linear patterns of traffic data. However, the promising results achieved on current public datasets may not be applicable to pra…
This paper addresses the problem of active collaborative localization in heterogeneous robot teams with unknown data association. It involves positioning a small number of identical unmanned ground vehicles (UGVs) at desired positions so that an unmanned aerial vehicle (UAV) can, through unlabelled…
This letter presents SW-LIO, a tightly coupled LiDAR-inertial odometry based on the sliding window approach. The proposed methodology encompasses rapid ground segmentation and the design of an iterative error-state Kalman filter (ESKF) to effectively fuse LiDAR point clouds and IMU measurements. By
Building suitable representations for diversified environments to enable robot autonomous navigation is a complicated task, especially for large-scale environments, where the captured vast amount of data will give rise to computation and storage bottlenecks. In this letter, we first propose the rand
Fast, autonomous flight in unstructured, cluttered environments such as forests is challenging because it requires the robot to compute new plans in realtime on a computationally-constrained platform. In this paper, we enable this capability with a search-based planning framework that adapts samplin…
Semantic maps represent the environment using a set of semantically meaningful objects. This representation is storage-efficient, less ambiguous, and more informative, thus facilitating large-scale autonomy and the acquisition of actionable information in highly unstructured, GPS-denied environments
The vast amount of data captured by robots in large-scale environments brings the computing and storage bottlenecks to the typical methods of modeling the spaces the robots travel in. In order to efficiently construct a compact terrain model from uncertain, incomplete point cloud data of large-scale…
We study self-supervised video representation learning, which is a challenging task due to 1) sufficient labels for supervision; 2) unstructured and noisy visual information. Existing methods mainly use contrastive loss with video clips as the instances and learn visual representation by discriminat…
Generating meaningful spatial models of physical environments is a crucial ability for autonomous navigation of mobile robots. This paper considers the problem of building continuous occupancy maps from sparse and noisy sensor data. To this end, we propose a new method named random mapping maps that…
The use of continuum manipulators in surgical applications can be beneficial because of their inherent safety from their structural compliance. However, the tip pose (position and orientation) accuracy of a continuum manipulator can be low when an external load or disturbance is applied. Closed-loop
We present a learning-based planner that aims to robustly drive a vehicle by mimicking human drivers’ driving behavior. We leverage a mid-to-mid approach that allows us to manipulate the input to our imitation learning network freely. With that in mind, we propose a novel feedback synthesizer for da…
Understanding the multi-scale visual information in a video is essential for Video Question Answering (VideoQA). Therefore, we propose a novel Multi-Scale Progressive Attention Network (MSPAN) to achieve relational reasoning between cross-scale video information. We construct clips of different leng…
To address the problem of building accurate and coherent models for large-scale terrains from incomplete and noisy sensor data, this paper proposes a novel framework that can efficiently infer terrain structures by divisionally providing the best linear unbiased estimates for the elevation values. T…
In this letter, we present a novel descriptor based on Urquhart tessellations derived from the position of trees in a forest. We propose a framework that uses these descriptors to detect previously seen observations and landmark correspondences, even with partial overlap and noise. We run loop closu
Existing learned-based image compression methods have shown impressive performance. However, most of them rely on the consistency of distribution between training images and test images, which limits the robustness of the trained model. In this paper, we propose a novel compression method called spa…
Needle-based procedures, such as biopsy and percutaneous tumor ablation, highly depend on the accuracy of needle placement. The accuracy is significantly affected by the needle-tissue interaction no matter what needles (straight or steerable) are used. Due to the unknown tissue mechanics, it is chal…
Gait recognition aims at identifying different people by the walking patterns, which can be conducted at a long distance without the cooperation of subjects. A key challenge for gait recognition is to learn representations from the silhouettes that are invariant to the factors such as clothing, carr…
Gait recognition, applied to identify individual walking patterns in a long-distance, is one of the most promising video-based biometric technologies. At present, most gait recognition methods take the whole human body as a unit to establish the spatio-temporal representations. However, we have obse…
Global context is crucial for 3D point cloud scene understanding tasks. In this work, we extended the contextual encoding layer that was originally designed for 2D tasks to 3D Point Cloud scenarios. The encoding layer learns a set of code words in the feature space of the 3D point cloud to characte…
This letter describes an end-to-end pipeline for tree diameter estimation based on semantic segmentation and lidar odometry and mapping. Accurate mapping of this type of environment is challenging since the ground and the trees are surrounded by leaves, thorns and vines, and the sensor typically exp
Panoptic segmentation, which needs to assign a category label to each pixel and segment each object instance simultaneously, is a challenging topic. Traditionally, the existing approaches utilize two independent models without sharing features, which makes the pipeline inefficient to implement. In a…
In this letter, we present a cheap, lightweight, and fast fruit counting pipeline. Our pipeline relies only on a monocular camera, and achieves counting performance comparable to a state-of-the-art fruit counting system that utilizes an expensive sensor suite including a monocular camera, LiDAR and
Huge training datasets for automatic speech recognition (ASR) typically contain redundant information so that a subset of data is generally enough to obtain similar ASR performance to that obtained when the entire dataset is employed for training. Although the centralized submodular-based data selec…
We present a novel fruit counting pipeline that combines deep segmentation, frame to frame tracking, and 3D localization to accurately count visible fruits across a sequence of images. Our pipeline works on image streams from a monocular camera, both in natural light, as well as with controlled illu…
In this work we propose a novel framework named DualNet aiming at learning more accurate representation for image recognition. Here two parallel neural networks are coordinated to learn complementary features and thus a wider network is constructed. Specifically, we logically divide an end-to-end de…
This paper presents a highway vehicle counting method in compressed domain, aiming at achieving acceptable estimation performance approaching the pixel-domain methods. Such a task essentially is challenging because the available information (e.g. motion vector) to describe vehicles in videos is quit…