26 accepted papers
Oil spills continuously affect marine ecosystems and require rapid monitoring for effective emergency response. This letter tackles the problem of persistent monitoring for continuously changing and scattered oil spill regions through Entropy Based Incremental Coverage Path Planning (EICPP). By usin
Oil spills continuously affect marine ecosystems and require rapid monitoring for effective emergency response. This letter tackles the problem of persistent monitoring for continuously changing and scattered oil spill regions through Entropy-Based Incremental Coverage Path Planning (EICPP). By usin…
Despite remarkable progress in driving world models, their potential for autonomous systems remains largely untapped: the world models are mostly learned for world simulation and decoupled from trajectory planning. While recent efforts aim to unify world modeling and planning in a single framework,…
With the rapid proliferation of 3D devices and the shortage of 3D content, stereo conversion is attracting increasing attention. Recent works introduce pretrained Diffusion Models (DMs) into this task. However, due to the scarcity of large-scale training data and comprehensive benchmarks, the optima…
Sales volume prediction, vital for strategic business planning, has always been a daunting task. With today’s data landscape brimming with diverse content from text to audio, and the rising influence of live streaming on sales data, the challenge becomes even more significant. The dense nature of li…
This paper aims to design monocular depth estimation models with better generalization abilities. To this end, we have conducted quantitative analysis and discovered two important insights. First, the Simulation Correlation phenomenon, commonly seen in long-tailed classification problems, also exist…
The completion of large occluded human body images poses a unique challenge for general image completion methods. The complex shape variations of human bodies make it difficult to establish a consistent understanding of their structures. Furthermore, as human vision is highly sensitive to human bodi…
Accurately predicting the volume of sales in live broadcast is crucial for e-commerce. Despite the success of the current sales volume prediction models, theirs application is significantly constrained by the absence of high-quality live sales volume data. In this paper, we introduce a novel applica…
Multimodal Large Language Model (MLLMs) leverages Large Language Models as a cognitive framework for diverse visual-language tasks. Recent efforts have been made to equip MLLMs with visual perceiving and grounding capabilities. However there still remains a gap in providing fine-grained pixel-level…
Multi-agent systems, when enhanced with Large Language Models (LLMs), exhibit profound capabilities in collective intelligence. However, the potential misuse of this intelligence for malicious purposes presents significant risks. To date, comprehensive research on the safety issues associated with m…
Compared with traditional RGB-only visual tracking, few datasets have been constructed for RGB-D tracking. In this paper, we propose ARKitTrack, a new RGB-D tracking dataset for both static and dynamic scenes captured by consumer-grade LiDAR scanners equipped on Apple's iPhone and iPad. ARKitTrack c…
Recent leading zero-shot video object segmentation (ZVOS) works devote to integrating appearance and motion information by elaborately designing feature fusion modules and identically applying them in multiple feature stages. Our preliminary experiments show that with the strong long-range dependenc…
Depth-aware panoptic segmentation is an emerging topic in computer vision which combines semantic and geometric understanding for more robust scene interpretation. Recent works pursue unified frameworks to tackle this challenge but mostly still treat it as two individual learning tasks, which limits…
"Unsupervised depth estimation using photometric losses suffers from local minimum and training instability. We address this issue by proposing an adaptive co-teaching framework to distill the learned knowledge from unsupervised teacher networks to a student network. We design an ensemble architectu…
"RGB-D salient object detection (SOD) enjoys significant advantages in understanding 3D geometry of the scene. However, the geometry information conveyed by depth maps are mostly under-explored in existing RGB-D SOD methods. In this paper, we propose a new framework to address this issue. We augment…
Deep learning-based image salient object detection (SOD) heavily relies on large-scale training data with pixel-wise labeling. High-quality labels involve intensive labor and are expensive to acquire. In this paper, we propose a novel multi-source uncertainty mining method to facilitate unsupervised…
We present YOFO (You Only inFer Once), a new paradigm for referring video object segmentation (RVOS) that operates in an one-stage manner. Our key insight is that the language descriptor should serve as target-specific guidance to identify the target object, while a direct feature fusion of image an…
Geometric constraints are shown to enforce scale consistency and remedy the scale ambiguity issue in self-supervised monocular depth estimation. Meanwhile, scale-invariant losses focus on learning relative depth, leading to accurate relative depth prediction. To combine the best of both worlds, we l…
Deep learning based visual trackers entail offline pre-training on large volumes of video datasets with accurate bounding box annotations that are labor-expensive to achieve. We present a new framework to facilitate bounding box annotations for video sequences, which investigates a selection-and-ref…
This paper proposes a hierarchical loss for monocular depth estimation, which measures the differences between the prediction and ground truth in hierarchical embedding spaces of depth maps. In order to find an appropriate embedding space, we design different architectures for hierarchical embedding…
Monocular depth estimation is an ill-posed problem, and as such critically relies on scene priors and semantics. Due to its complexity, we propose a deep neural network model based on a semantic divide-and-conquer approach. Our model decomposes a scene into semantic segments, such as object instance…
Local structure of target objects are essential for robust tracking. However, existing methods based on deep neural networks mostly describe the target appearance from the global view, leading to high sensitivity to non-rigid appearance change and partial occlusion. In this paper, we circumvent this…
Deep Neural Networks (DNNs) have substantially improved the state-of-the-art in salient object detection. However, training DNNs requires costly pixel-level annotations. In this paper, we leverage the observation that image-level tags provide important cues of foreground salient objects, and develop…
Due to the limited amount of training samples, fine-tuning pre-trained deep models online is prone to over-fitting. In this paper, we propose a sequential training method for convolutional neural networks (CNNs) to effectively transfer pre-trained deep features for online applications. We regard a C…
This paper presents a saliency detection algorithm by integrating both local estimation and global search. In the local estimation stage, we detect local saliency by using a deep neural network (DNN-L) which learns local patch features to determine the saliency value of each pixel. The estimated loc…
We propose a new approach for general object tracking with fully convolutional neural network. Instead of treating convolutional neural network (CNN) as a black-box feature extractor, we conduct in-depth study on the properties of CNN features offline pre-trained on massive image data and classifica…