58 accepted papers
Narrow passage scenarios pose significant challenges for path planning, especially for tasks requiring real-time performance. Traditional asymptotically converging sampling-based planners (SBPs) often exhibit poor initial path quality and slow convergence, limiting their ability to efficiently const
Cooperative perception significantly enhances scene understanding by integrating complementary information from diverse agents. However, existing research often overlooks critical challenges inherent in real-world multi-source data integration, specifically high temporal latency and multi-source noi
What if the next generation of human-computer interaction is not a screen... but a conversation? Large Language Models (LLMs) offer a new paradigm for interacting with computers through text, but they lack shape reasoning capabilities. We introduce Textual Anatomy Encoding (TAE), a workflow that con
Navigational bronchoscopy is critical for pulmonary interventions, yet current platforms depend heavily on pre-operative CT or external sensors, limiting their use in critical care and resource-constrained settings. Vision-only navigation offers a scalable alternative, but conventional visual odomet…
Recent rapid advancement of generative models has significantly improved the fidelity and accessibility of AI-generated synthetic images. While enabling various innovative applications, the unprecedented realism of these synthetics makes them increasingly indistinguishable from authentic photographs
Unified multimodal models (UMMs) have shown remarkable advances in jointly understanding and generating text and images. However, prevailing evaluations treat these abilities in isolation, such that tasks with multimodal inputs and outputs are scored primarily through unimodal reasoning: textual ben…
We present Segment Anything Model (SAM) 3, a unified model that detects, segments, and tracks objects in images and videos based on concept prompts, which we define as either short noun phrases (e.g., “yellow school bus”), image exemplars, or a combination of both. Promptable Concept Segmentation (P…
Surgical workflow prediction is critical for enhancing safety and providing real-time guidance in Computer-Assisted Surgery (CAS), particularly in laparoscopic and Robot-Assisted Surgery (RAS). We propose a novel visual information-based method for predicting surgical workflows at fine temporal scal
This paper studies Visual Question-Visual Answering (VQ-VA): generating an image, rather than text, in response to a visual question---an ability that has recently emerged in proprietary systems such as NanoBanana and GPT-Image. To also bring this capability to open-source models, we introduce VQ-VA
To address the challenge of high annotation costs in text-to-speech (TTS) generation, this paper introduces a semi-supervised learning framework specifically designed for low-resource TTS scenarios. The framework incorporates adaptive thresholding to select appropriate pseudo-labels and leverages au…
Zero-shot learning (ZSL) endeavors to transfer knowledge from the seen categories to recognize unseen categories, which mostly relies on the semantic-visual interactions between image and attribute tokens. Recently, the prompt learning has emerged in ZSL and demonstrated significant potential as it…
Existing metrics often lack the granularity and interpretability to capture nuanced clinical differences between candidate and ground-truth radiology reports, resulting in suboptimal evaluation. We introduce a **Cl**inically grounded tabular framework with **E**xpert-curated labels and **A**ttribute
Continuous space-time video super-resolution (C-STVSR) endeavors to upscale videos simultaneously at arbitrary spatial and temporal scales, which has recently garnered increasing interest. However, prevailing methods struggle to yield satisfactory videos at out-of-distribution spatial and temporal s…
Self-balancing lower limb rehabilitation exoskeletons (SLLREs) allow individuals with lower limb dysfunction to walk without the use of crutches. Stable and human-like walking motions are crucial for SLLREs because achieving a close imitation of healthy human walking is a key goal in rehabilitation
Visual instruction tuning has made considerable strides in enhancing the capabilities of Large Multimodal Models (LMMs). However, existing open LMMs largely focus on single-image tasks, their applications to multi-image scenarios remains less explored. Additionally, prior LMM research separately tac…
The clinical diagnosis of most mental disorders primarily relies on the conversations between psychiatrist and patient. The creation of such diagnostic conversation datasets is promising to boost the AI mental healthcare community. However, directly collecting the conversations in real diagnosis sce…
Comprehensive evaluation of Multimodal Large Language Models (MLLMs) has recently garnered widespread attention in the research community. However, we observe that existing benchmarks present several common barriers that make it difficult to measure the significant challenges that models face in the…
Although recent generative image compression methods have demonstrated impressive potential in optimizing the rate-distortion-perception trade-off, they still face the critical challenge of flexible rate adaptation to diverse compression necessities and scenarios. To overcome this challenge, this pa…
Sign Language Production (SLP) aims to generate semantically consistent sign videos from textual statements, where the conversion from textual glosses to sign poses (G2P) is a crucial step. Existing G2P methods typically treat sign poses as discrete three-dimensional coordinates and directly fit the…
Dynamic quantization has attracted rising attention in image super-resolution (SR) as it expands the potential of heavy SR models onto mobile devices while preserving competitive performance. Most current methods explore layer-to-bit configuration upon varying local regions, adaptively allocating th…
In this paper, considering overall deformations of the exoskeleton, we couple deformations relationship network (DRN) with fractional order viscoelastic (FOV) controller, proposing a novel DRN-FOV closed-loop control method, endowing exoskeleton with stable dynamic walking ability. Simply by utilizi
"In this paper, we develop an open-set object detector, called Grounding DINO, by marrying Transformer-based detector DINO with grounded pre-training, which can detect arbitrary objects with human inputs such as category names or referring expressions. The key solution of open-set object detection i…
Foundation models possess strong capabilities in reasoning and memorizing across modalities. To further unleash the power of foundation models, we present FIND, a generalized interface for aligning foundation models' embeddings with unified image and dataset-level understanding spanning modality and…
"With the recent significant advancements in large multimodal models (LMMs), the importance of their grounding capability in visual chat is increasingly recognized. Despite recent efforts to enable LMMs to support grounding, their capabilities for grounding and chat are usually separate, and their c…
"This paper presents (), a general-purpose multimodal assistant trained using an end-to-end approach that systematically expands the capabilities of large multimodal models (LMMs). maintains a skill repository that contains a wide range of vision and vision-language pre-trained models (tools), and i…
"We present , a highly practical model for open-set object detection. Previous open-set object detection methods relying on text prompts effectively encapsulate the abstract concept of common objects, but struggle with rare or complex object representation due to data scarcity and descriptive limita…
Convolutional neural networks (CNNs) have been extensively used in image classification. However, it is still challenging to directly deploy them on edge devices because of high computation requirements. To solve this problem, many pruning schemes for neural networks have been proposed. However, the…
"In this paper, we propose a simple yet effective approach for Tracking Any Point with TRansformers (). Based on the observation that point tracking bears a great resemblance to object detection and tracking, we borrow designs from DETR-like algorithms to address the task of TAP. In , in each video…
In this paper, we present TAPTRv2, a Transformer-based approach built upon TAPTR for solving the Tracking Any Point (TAP) task. TAPTR borrows designs from DEtection TRansformer (DETR) and formulates each tracking point as a point query, making it possible to leverage well-studied operations in DETR-…
In-context prompting in large language models (LLMs) has become a prevalent approach to improve zero-shot capabilities but this idea is less explored in the vision domain. Existing visual prompting methods focus on referring segmentation to segment the most relevant object falling short of addressin…
In this work, we present OpenSeeD, a simple Open-vocabulary Segmentation and Detection framework that learns from different segmentation and detection datasets. To bridge the gap of vocabulary and annotation granularity, we first introduce a pretrained text encoder to encode all the visual concepts…
In this paper, we propose a new operator, called 3D DeFormable Attention (DFA3D), for 2D-to-3D feature lifting, which transforms multi-view 2D image features into a unified 3D space for 3D object detection. Existing feature lifting approaches, such as Lift-Splat-based and 2D attention-based, either…
We present DINO (DETR with Improved deNoising anchOr boxes), a strong end-to-end object detector. DINO improves over previous DETR-like models in performance and efficiency by using a contrastive way for denoising training, a look forward twice scheme for box prediction, and a mixed query selection…
In this paper, we study the problem of visual grounding by considering both phrase extraction and grounding (PEG). In contrast to the previous phrase-known-at-test setting, PEG requires a model to extract phrases from text and locate objects from image simultaneously, which is a more practical setti…
This paper is concerned with the matching stability problem across different decoder layers in DEtection TRansformers (DETR). We point out that the unstable matching in DETR is caused by a multi-optimization path problem, which is highlighted by the one-to-one matching design in DETR. To address thi…
This paper presents a novel end-to-end framework with Explicit box Detection for multi-person Pose estimation, called ED-Pose, where it unifies the contextual learning between human-level (global) and keypoint-level (local) information. Different from previous one-stage methods, ED-Pose re-considers…
Continual learning aims to efficiently learn from a non-stationary stream of data while avoiding forgetting the knowledge of old data. In many practical applications, data complies with non-Euclidean geometry. As such, the commonly used Euclidean space cannot gracefully capture non-Euclidean geometr…
Recent DEtection TRansformer-based (DETR) models have obtained remarkable performance. Its success cannot be achieved without the re-introduction of multi-scale feature fusion in the encoder. However, the excessively increased tokens in multi-scale features, especially for about 75% of low-level fea…
We present a mask-piloted Transformer which improves masked-attention in Mask2Former for image segmentation. The improvement is based on our observation that Mask2Former suffers from inconsistent mask predictions between consecutive decoder layers, which leads to inconsistent optimization goals and…
In this paper we present Mask DINO, a unified object detection and segmentation framework. Mask DINO extends DINO (DETR with Improved Denoising Anchor Boxes) by adding a mask prediction branch which supports all image segmentation tasks (instance, panoptic, and semantic). It makes use of the query e…
This work proposes an end-to-end neural interactive keypoint detection framework named Click-Pose, which can significantly reduce more than 10 times labeling costs of 2D keypoint annotation compared with manual-only annotation. Click-Pose explores how user feedback can cooperate with a neural keypoi…
Generalized Zero-Shot Learning (GZSL) identifies unseen categories by knowledge transferred from the seen domain, relying on the intrinsic interactions between visual and semantic information. Prior works mainly localize regions corresponding to the sharing attributes. When various visual appearance…
In this work, we present SEEM, a promotable and interactive model for segmenting everything everywhere all at once in an image. In SEEM, we propose a novel and versatile decoding mechanism that enables diverse prompting for all types of segmentation tasks, aiming at a universal interface that behave…
In many web applications, deep learning-based CTR prediction models (deep CTR models for short) are widely adopted. Traditional deep CTR models learn patterns in a static manner, i.e., the network parameters are the same across all the instances. However, such a manner can hardly characterize each…
The decomposition of multi-subject fMRI data using rank-(L,L,1,1) block term decomposition (BTD) can preserve higher-way data structure and is more robust to noise effects by decomposing shared spatial maps (SMs) into a product of two rank-L loading matrices. However, since the number of whole-brain…
We present in this paper a novel query formulation using dynamic anchor boxes for DETR (DEtection TRansformer) and offer a deeper understanding of the role of queries in DETR. This new formulation directly uses box coordinates as queries in Transformer decoders and dynamically updates them layer by…
We present in this paper a novel denoising training method to speedup DETR (DEtection TRansformer) training and offer a deepened understanding of the slow convergence issue of DETR-like methods. We show that the slow convergence results from the instability of bipartite graph matching which causes i…
The Transformer architecture has led to significant gains in machine translation. However, most studies focus on only sentence-level translation without considering the context dependency within documents, leading to the inadequacy of document-level coherence. Some recent research tried to mitigate…
Multilingual pretrained models have shown strong cross-lingual transfer ability. Some works used code-switching sentences, which consist of tokens from multiple languages, to enhance the cross-lingual representation further, and have shown success in many zero-shot cross-lingual tasks. However, code…
A mass of experiments shows that the pose of the input 3D models exerts a tremendous influence on automatic 3D shape analysis. In this paper, we propose Upright-Net, a deep-learning-based approach for estimating the upright orientation of 3D point clouds. Based on a well-known postulate of design st…
In recent years, convolutional neural networks (CNNs) have become a prominent tool for texture recognition. The key of existing CNN-based approaches is aggregating the convolutional features into a robust yet discriminative description. This paper presents a novel feature aggregation module called C…
Existing convolutional neural networks (CNNs) often use global average pooling (GAP) to aggregate feature maps into a single representation. However, GAP cannot well characterize complex distributive patterns of spatial features while such patterns play an important role in texture-oriented applicat…
Dialogue systems in open domain have achieved great success due to the easily obtained single-turn corpus and the development of deep learning, but the multi-turn scenario is still a challenge because of the frequent coreference and information omission. In this paper, we investigate the incomplete…
The wide-angle lens gains increasing attention since it can capture a wide field-of-view scene (FoV). However, the obtained image is contaminated with radial distortion, making the scene not realistic. Previous distortion rectification methods rectify the image in a rectangle or invagination, failin…
Depth maps obtained by commercial depth sensors are always in low-resolution, making it difficult to be used in various computer vision tasks. Thus, depth map super-resolution (SR) is a practical and valuable task, which upscales the depth map into high-resolution (HR) space. However, limited by the…
Recently, Convolutional Neural Networks (CNN) based image super-resolution (SR) have shown significant success in the literature. However, these methods are implemented as single-path stream to enrich feature maps from the input for the final prediction, which fail to fully incorporate former low-le…
Discriminative Correlation Filters (DCF) are efficient in visual tracking but suffer from unwanted boundary effects. Spatially Regularized DCF (SRDCF) has been suggested to resolve this issue by enforcing spatial penalty on DCF coefficients, which, inevitably, improves the tracking performance at th…
The micro-Doppler is an effective tool for target recognition. It is hard to detect micro-Doppler induced by vibration for its small value. In our system, phase-modulated stepped-frequency waveform is used. The method of matching pursuit (MP) is introduced to compensate translation. Translation traj…