104 accepted papers
While reinforcement learning (RL) has proven highly effective for general reasoning in vision-language models, its application to tasks requiring deep understanding of information-rich images and structured output generation remains underexplored. Chart-to-code generation exemplifies this challenge,…
Large vision-language models (LVLMs) have shown remarkable capabilities in visual-language understanding. Despite their success, LVLMs still suffer from generating hallucinations in complex generation tasks, leading to inconsistencies between visual inputs and generated content. To address this issu
Weakly supervised 3D instance segmentation is essential for 3D scene understanding, especially as the growing scale of data and high annotation costs associated with fully supervised approaches. Existing methods primarily rely on two forms of weak supervision: one-thing-one-click annotations and bou
We present Gen3R, a method that bridges the strong priors of foundational reconstruction models and video diffusion models for scene-level 3D generation. We repurpose the VGGT reconstruction model to produce geometric latents by training an adapter on its tokens, which are regularized to align with
In recent years, electroencephalography (EEG)-based visual decoding research has become a key direction for revealing brain processing mechanisms and realizing brain-computer interfaces. This emerging field has attracted extensive attention in the fields of brain science, cognitive neuroscience, and
Text-to-video generation has significantly enriched content creation and holds the potential to evolve into powerful world simulators. However, modeling the vast spatiotemporal space remains computationally demanding, particularly when employing Transformers, which incur quadratic complexity in sequ
Multimodal large language models (MLLMs) have achieved remarkable performance across a wide range of vision-language tasks. However, their ability in low-level visual perception, particularly in detecting fine-grained visual discrepancies, remains underexplored and lacks systematic analysis.In this
Multimodal large language models are progressively advancing toward multimodal agents that can proactively execute tasks. Existing research on multimodal agents primarily targets either GUI or embodied scenarios, corresponding to interactions within 2D virtual world and 3D physical world, respective…
Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced the reasoning capabilities of Large Language Models (LLMs) and is now being applied to Vision-Language Models (VLMs). However, vanilla RLVR for VLMs verifies only the final textual output, critically neglecting the foun
Reading text from images or scanned documents via OCR models has been a longstanding focus of researchers. Intuitively, text reading is perceived as a straightforward perceptual task, and existing work primarily focuses on constructing enriched data engineering to enhance SFT capabilities. In this w
Panoramic depth estimation enables a complete 360^\circ understanding of 3D environments but faces significant challenges in generalizing to real-world scenes. While recent zero-shot depth models like Depth Anything achieve remarkable generalization on perspective images, their performance sharply d
Reinforcement learning (RL) with verifiable rewards has recently catalyzed a wave of “MLLM-r1” approaches that bring RL to vision language models. Most representative paradigms begin with a cold start, typically employing supervised fine-tuning (SFT), to initialize the policy before RL. However, SFT…
Vector quantization (VQ) is a key component in discrete tokenizers for image generation, but its training is often unstable due to straight-through estimation bias, one-step-behind updates, and sparse codebook gradients, which lead to suboptimal reconstruction performance and low codebook usage. In…
We present StereoWorld, a camera-conditioned stereo world model that jointly learns appearance and binocular geometry for end-to-end stereo video generation.Unlike monocular RGB or RGBD approaches, StereoWorld operates exclusively within the RGB modality, while simultaneously grounding geometry dire
Distinct from attention-based compression methods, this paper presents an information uniqueness driven video compression framework, termed UniComp, which aims to maximize the information fidelity of video representations under constrained computational budgets. Starting from the information-theoret
Large Language Models (LLMs) demonstrate strong capabilities in broad knowledge representation, yet they are inherently deficient in pixel-level perceptual understanding. Although the Segment Anything Model (SAM) represents a significant advancement in visual-prompt-driven image segmentation, it exh
LLM-based agents have demonstrated impressive zero-shot performance in vision-language navigation (VLN) task. However, existing LLM-based methods often focus only on solving high-level task planning by selecting nodes in predefined navigation graphs for movements, overlooking low-level control in na…
Existing end-to-end Multi-Object Tracking (e2e-MOT) methods have not surpassed non-end-to-end tracking-by-detection methods. One possible reason lies in the training label assignment strategy that consistently binds the tracked objects with tracking queries and assigns few newborns to detection quer…
Climate downscaling is crucial for detailed small- scale analysis and for acquiring climate data in regions without weather stations. Operator learning has proven potential for this task. However, several challenges remain in operator learning, such as multimodal fusion, spatiotemporal fusion and in…
Visual self-localization technology is essential for unmanned aerial vehicles(UAVs) to achieve autonomous navigation and mission execution in environments where global navigation satellite system (GNSS) signals are unavailable. This technology estimates the UAV's geographic location by performing cr
Despite advances in general video understanding, Video Large Language Models (Video-LLMs) face challenges in precise temporal localization due to discrete time representations and limited temporally aware datasets. Existing methods for temporal expression either conflate time with text-based numeric…
This work challenges the residual prediction paradigm in visual autoregressive modeling and presents FlexVAR, a new Flexible Visual AutoRegressive image generation paradigm. FlexVAR facilitates autoregressive learning with ground-truth prediction, enabling each step to independently produce plausibl…
Fine-grained open-vocabulary object detection (FG-OVD) aims to detect novel object categories described by attribute-rich texts. While existing open-vocabulary detectors show promise at the base-category level, they underperform in fine-grained settings due to the semantic entanglement of subjects a…
The deep operator networks (DON), a class of neural operators that learn mappings between function spaces, have recently emerged as surrogate models for parametric partial differential equations (PDEs). However, their full potential for accurately approximating general black-box PDEs remains underex
Multi-label causal feature selection has garnered considerable attention for its ability to identify the most informative features while accounting for the causal dependencies between labels and features. However, previous work often overlooks the unique contributions of labels to the target variabl
Instruction tuning has underscored the significant potential of large language models (LLMs) in producing more human controllable and effective outputs in various domains. In this work, we focus on the data selection problem for task-specific instruction tuning of LLMs. Prevailing methods primarily
In language-guided visual navigation, agents locate target objects in unseen environments using natural language instructions. For reliable navigation in unfamiliar scenes, agents should possess strong perception, planning, and prediction capabilities. Additionally, when agents revisit previously ex…
Large Multimodal Models (LMMs) have demonstrated exceptional comprehension and interpretation capabilities in Autonomous Driving (AD) by incorporating large language models. Despite the advancements, current data-driven AD approaches tend to concentrate on a single dataset and specific tasks, neglec…
Recently, robotics has advanced significantly through the integration of larger models and large-scale datasets. However, challenges remain in applying these models to 3D spatial interactions and managing data collection costs. To address these issues, we propose the multimodal robotic manipulation…
Collecting real-world data for rare high-risk scenarios, long-tailed driving events, and complex interactions remains challenging, leading to poor performance of existing autonomous driving systems in these critical situations. In this paper, we propose RoboTron-Sim that improves real-world driving…
Automated medication recommendation is a crucial task within the domain of artificial intelligence in healthcare, where recommender systems are supposed to deliver precise, personalized drug combinations tailored to the evolving health states of patients. Existing approaches often treat clinical rec
Real-world time series inherently exhibit significant non-stationarity, posing substantial challenges for forecasting. To address this issue, this paper proposes a novel prediction framework, TimeStacker, designed to overcome the limitations of existing models in capturing the characteristics of non…
In this work, we first revisit the sampling issues in current autoregressive (AR) image generation models and identify that image tokens, unlike text tokens, exhibit lower information density and non-uniform spatial distribution. Accordingly, we present an entropy-informed decoding strategy that fac…
Aiming to predict the complete shape of partially occluded objects, amodal segmentation is an important capacity towards visual intelligence. In order to promote the practicability, zero-shot foundation model competent for the open world gains growing attention in this field. Nevertheless, prior mod…
Despite the success of Vision-Language Models (VLMs) like CLIP in aligning vision and language, their proficiency in detailed, fine-grained visual comprehension remains a key challenge. We present CLIP-IN, a novel framework that bolsters CLIP's fine-grained perception through two core innovations. F…
Conventional Vision Transformer streamlines visual modeling by employing a uniform input resolution, which underestimates the inherent variability of natural visual data and incurs a cost in spatial-contextual fidelity. While preliminary explorations have superficially investigated native resolution…
"In this paper, we propose 3DSS-VLG, a weakly supervised approach for 3D Semantic Segmentation with 2D Vision-Language Guidance, an alternative approach that a 3D model predicts dense-embedding for each point which is co-embedded with both the aligned image and text spaces from the 2D vision-languag…
In this paper, we propose a new setting for generating product descriptions from images, augmented by marketing keywords. It leverages the combined power of visual and textual information to create descriptions that are more tailored to the unique features of products. For this setting, previous met…
Powered by massive curated training data Segment Anything Model (SAM) has demonstrated its impressive generalization capabilities in open-world scenarios with the guidance of prompts. However the vanilla SAM is class-agnostic and heavily relies on user-provided prompts to segment objects of interest…
We aim at exploiting additional auxiliary labels from an independent (auxiliary) task to boost the primary task performance which we focus on, while preserving a single task inference cost of the primary task. While most existing auxiliary learning methods are optimization-based relying on loss weig…
Neural Radiance Fields (NeRF) have demonstrated impressive potential in synthesizing novel views from dense input, however, their effectiveness is challenged when dealing with sparse input. Existing approaches that incorporate additional depth or semantic supervision can alleviate this issue to an e…
Electroencephalography (EEG) is crucial for recording brain activity, with applications in medicine, neuroscience, and brain-computer interfaces (BCI). However, challenges such as low signal-to-noise ratio (SNR), high inter-subject variability, and channel mismatch complicate the extraction of…
In this paper we present a novel paradigm to enhance the ability of object detector e.g. expanding categories or improving detection performance by training on syn- thetic dataset generated from diffusion models. Specifically we integrate an instance-level grounding head into a pre- trained generati…
Camera-based bird-eye-view (BEV) perception paradigm has made significant progress in the autonomous driving field. Under such a paradigm, accurate BEV representation construction relies on reliable depth estimation for multi-camera images. However, existing approaches exhaustively predict depths fo…
Referring 3D Segmentation is a visual-language task that segments all points of the specified object from a 3D point cloud described by a sentence of query. Previous works perform a two-stage paradigm, first conducting language-agnostic instance segmentation then matching with given text query. Howe…
Large Multimodal Model (LMM) is a hot research topic in the computer vision area and has also demonstrated remarkable potential across multiple disciplinary fields. A recent trend is to further extend and enhance the perception capabilities of LMMs. The current methods follow the paradigm of adaptin…
"Data-driven approaches for autonomous driving (AD) have been widely adopted in the past decade but are confronted with dataset bias and uninterpretability. Inspired by the knowledge-driven nature of human driving, recent approaches explore the potential of large language models (LLMs) to improve un…
This paper aims to address a common challenge in deep learning-based image transformation methods such as image enhancement and super-resolution which heavily rely on precisely aligned paired datasets with pixel-level alignments. However creating precisely aligned paired images presents significant…
Video representation is a long-standing problem that is crucial for various downstream tasks, such as tracking, depth prediction, segmentation, view synthesis, and editing. However, current methods either struggle to model complex motions due to the absence of 3D structure or rely on implicit 3D rep…
Tables contrast with unstructured text data by its structure to organize the information.In this paper, we investigate the efficiency of various LLMs in interpreting tabular data through different prompting strategies and data formats. Our analysis extends across six benchmarks for table-related tas…
"Temporal Action Detection (TAD) focuses on detecting pre-defined actions, while Moment Retrieval (MR) aims to identify the events described by open-ended natural language within untrimmed videos. Despite that they focus on different events, we observe they have a significant connection. For instanc…
Conditional inference on joint textual and visual clues is a multi-modal reasoning task that textual clues provide prior permutation or external knowledge, which are complementary with visual content and pivotal to deducing the correct option. Previous methods utilizing pretrained vision-language mo…
Pretrained Vision-Language Models (VLMs) have achieved remarkable performance in image retrieval from text. However, their performance drops drastically when confronted with linguistically complex texts that they struggle to comprehend. Inspired by the Divide-and-Conquer algorithm and dual-process t…
Object re-identification (ReID) aims to find instances with the same identity as the given probe from a large gallery. Pairwise losses play an important role in training a strong ReID network. Existing pairwise losses densely exploit each instance as an anchor and sample its triplets in a mini-batch…
Recent LSS-based multi-view 3D object detection has made tremendous progress, by processing the features in Brid-Eye-View (BEV) via the convolutional detector. However, the typical convolution ignores the radial symmetry of the BEV features and increases the difficulty of the detector optimization.…
Video Grounding (VG) aims to locate the desired segment from a video given a sentence query. Recent studies have found that current VG models are prone to over-rely the groundtruth moment annotation distribution biases in the training set. To discourage the standard VG model's behavior of exploiting…
Recently, feature-based methods for Online Action Detection (OAD) have been gaining traction. However, these methods are constrained by their fixed backbone design, which fails to leverage the potential benefits of a trainable backbone. This paper introduces an end-to-end learning network that revis…
Fusing LiDAR and camera information is essential for accurate and reliable 3D object detection in autonomous driving systems. This is challenging due to the difficulty of combining multi-granularity geometric and semantic features from two drastically different modalities. Recent approaches aim at e…
Recently, the open-vocabulary semantic segmentation problem has attracted increasing attention and the best performing methods are based on two-stream networks: one stream for proposal mask generation and the other for segment classification using a pre-trained visual-language model. However, existi…
Assembly Sequence Planning (ASP) is the essential process for modern manufacturing, proven to be NP-complete thus its effective and efficient solution has been a challenge for researchers in the field. In this paper, we present a graph-transformer based framework for the ASP problem which is trained…
The adversarial attacks have attracted increasing attention in various fields including natural language processing. The current textual attacking models primarily focus on fooling models by adding character-/word-/sentence-level perturbations, ignoring their influence on human perception. In this p…
Despite the tremendous progress in neural radiance fields (NeRF), we still face a dilemma of the trade-off between quality and efficiency, e.g., MipNeRF presents fine-detailed and anti-aliased renderings but takes days for training, while Instant-ngp can accomplish the reconstruction in a few minute…
In this paper, we present a one-stage framework TriDet for temporal action detection. Existing methods often suffer from imprecise boundary predictions due to the ambiguous action boundaries in videos. To alleviate this problem, we propose a novel Trident-head to model the action boundary via an est…
Generating precise class-aware pseudo ground-truths, a.k.a, class activation maps (CAMs), is essential for Weakly-Supervised Semantic Segmentation. The original CAM method usually produces incomplete and inaccurate localization maps. To tackle with this issue, this paper proposes an Expansion and Sh…
Weakly supervised temporal sentence grounding aims to temporally localize the target segment corresponding to a given natural language query, where it provides video-query pairs without temporal annotations during training. Most existing methods use the fused visual-linguistic feature to reconstruct…
"3D dense captioning is a recently-proposed novel task, where point clouds contain more geometric information than the 2D counterpart. However, it is also more challenging due to the higher complexity and wider variety of inter-object relations contained in point clouds. Existing methods only treat…
"The goal of this work is to establish a scalable pipeline for expanding an object detector towards novel/unseen categories, using zero manual annotations. To achieve that, we make the following four contributions: (i) in pursuit of generalisation, we propose a two-stage open-vocabulary object detec…
"This work aims at advancing temporal action detection (TAD) using an encoder-decoder framework with action queries, similar to DETR, which has shown great success in object detection. However, the framework suffers from several problems if directly applied to TAD: the insufficient exploration of in…
In this paper, we propose a novel method to mine the commonsense knowledge shared between the video and text modalities for video-text retrieval, namely visual consensus modeling. Different from the existing works, which learn the video and text representations and their complicated relationships so…
Visual grounding, which aims to build a correspondence between visual objects and their language entities, plays a key role in cross-modal scene understanding. One promising and scalable strategy for learning visual grounding is to utilize weak supervision from only image-caption pairs. Previous met…
Image-text matching plays a critical role in bridging the vision and language, and great progress has been made by exploiting the global alignment between image and sentence, or local alignments between regions and words. However, how to make the most of these alignments to infer more accurate match…
Rain is a common natural phenomenon. Taking images in the rain however often results in degraded quality of images, thus compromises the performance of many computer vision systems. Most existing de-rain algorithms use only one single input image and aim to recover a clean image. Few work has exploi…
Image-text matching plays a central role in bridging vision and language. Most existing approaches only rely on the image-text instance pair to learn their representations, thereby exploiting their matching relationships and making the corresponding alignments. Such approaches only exploit the super…
As the basic building block of Convolutional Neural Networks (CNNs), the convolutional layer is designed to extract local patterns and lacks the ability to model global context in its nature. Many efforts have been recently devoted to complementing CNNs with the global modeling ability, especially b…
Referring expression comprehension (REF) aims at identifying a particular object in a scene by a natural language expression. It requires joint reasoning over the textual and visual domains to solve the problem. Some popular referring expression datasets, however, fail to provide an ideal test bed f…
Existing deep learning methods for image deblurring typically train models using pairs of sharp images and their blurred counterparts. However, synthetically blurring images does not necessarily model the blurring process in real-world scenarios with sufficient accuracy. To address this problem, we…
Existing image-to-image transformation approaches primarily focus on synthesizing visually pleasing data. Generating images with correct identity labels is challenging yet much less explored. It is even more challenging to deal with image transformation tasks with large deformation in poses, viewpoi…
Integrated robotic arm system should contain both grasp and place actions. However, most grasping methods focus more on how to grasp objects, while ignoring the placement of the grasped objects, which limits their applications in various industrial environments. In this research, we propose a model-…
In this paper, we propose to guide the video caption generation with Part-of-Speech (POS) information, based on a gated fusion of multiple representations of input videos. We construct a novel gated fusion network, with one particularly designed cross-gating (CG) block, to effectively encode and fus…
In this paper, we propose one novel model for point cloud semantic segmentation,which exploits both the local and global structures within the point cloud based onthe contextual point representations. Specifically, we enrich each point represen-tation by performing one novel gated fusion on the poin…
Humans can robustly learn novel visual concepts even when images undergo various deformations and loose certain information. Mimicking the same behavior and synthesizing deformed instances of new concepts may help visual recognition systems perform better one-shot learning, i.e., learning concepts f…
Gait recognition is an important biometric method popularly used in video surveillance, where the task is to identify people at a distance by their walking patterns from video sequences. Most of the current successful approaches for gait recognition either use a pair of gait images to form a cross-g…
We tackle the human motion imitation, appearance transfer, and novel view synthesis within a unified framework, which means that the model once being trained can be used to handle all these tasks. The existing task-specific methods mainly use 2D keypoints (pose) to estimate the human body structure.…
Temporal action proposal generation is an important task, aiming to localize the video segments containing human actions in an untrimmed video. In this paper, we propose a multi-granularity generator (MGG) to perform the temporal action proposal from different granularity perspectives, relying on th…
Temporal sentence grounding in videos aims to detect and localize one target video segment, which semantically corresponds to a given sentence. Existing methods mainly tackle this task via matching and aligning semantics between a sentence and candidate video segments, while neglect the fact that th…
The need for efficiently finding the video content a user wants is increasing because of the erupting of user-generated videos on the Web. Existing keyword-based or content-based video retrieval methods usually determine what occurs in a video but not when and where. In this paper, we make an answer…
Deep neural networks have achieved great successes on the image captioning task. However, most of the existing models depend heavily on paired image-sentence datasets, which are very expensive to acquire. In this paper, we make the first attempt to train an image captioning model in an unsupervised…
Dense video captioning is a newly emerging task that aims at both localizing and describing all events in a video. We identify and tackle two challenges on this task, namely, (1) how to utilize both past and future contexts for accurate event proposal predictions, and (2) how to construct informativ…
In this paper, we present a deep convolutional neural network to capture the inherent properties of image degradation, which can handle different kernels and saturated pixels in a unified framework. The proposed neural network is motivated by the low-rank property of pseudo-inverse kernels. We firs…
In this paper, we propose an efficient algorithm to directly restore a clear image from a hazy input. The proposed algorithm hinges on an end-to-end trainable neural network that consists of an encoder and a decoder. The encoder is exploited to capture the context of the derived input images, while…
Taking a photo outside, can we predict the immediate future, e.g., how would the cloud move in the sky? We address this problem by presenting a generative adversarial network (GAN) based two-stage approach to generating realistic time-lapse videos of high resolution. Given the first frame, our model…
Neural style transfer is an emerging technique which is able to endow daily-life images with attractive artistic styles. Previous work has succeeded in applying convolutional neural networks (CNNs) to style transfer for monocular images or videos. However, style transfer for stereoscopic images is s…
We propose a parsimonious quantile regression framework to learn the dynamic tail behaviors of financial asset returns. Our model captures well both the time-varying characteristic and the asymmetrical heavy-tail property of financial time series. It combines the merits of a popular sequential neura…
In this paper, the problem of describing visual contents of a video sequence with natural language is addressed. Unlike previous video captioning work mainly exploiting the cues of video contents to make a language description, we propose a reconstruction network (RecNet) with a novel encoder-decode…
Recently, much advance has been made in image captioning, and an encoder-decoder framework has been adopted by all the state-of-the-art models. Under this framework, an input image is encoded by a convolutional neural network (CNN) and then translated into natural language with a recurrent neural ne…
Recently, caption generation with an encoder-decoder framework has been extensively studied and applied in different domains, such as image captioning, code captioning, and so on. In this paper, we propose a novel architecture, namely Auto-Reconstructor Network (ARNet), which, coupling with the conv…
Submodular functions are discrete analogs of convex functions, which have applications in various fields, including machine learning and computer vision. However, in large-scale applications, solving Submodular Function Minimization (SFM) problems remains challenging. In this paper, we make the firs…
Recent studies on unsupervised image-to-image translation have made remarkable progress by training a pair of generative adversarial networks with a cycle-consistent loss. However, such unsupervised methods may generate inferior results when the image resolution is high or the two image domains are…
Many methods have been developed to help people find the video content they want efficiently. However, there are still some unsolved problems in this area. For example, given a query video and a reference video, how to accurately localize a segment in the reference video such that the segment semant…
Recent research endeavors have shown the potential of using feed-forward convolutional neural networks to accomplish fast style transfer for images. In this work, we take one step further to explore the possibility of exploiting a feed-forward network to perform style transfer for videos and simulta…
Subspace models have been widely used for appearance based object tracking. Most existing subspace based trackers employ a linear subspace to represent object appearances, which are not accurate enough to model large variations of objects. To address this, this paper presents a local subspace collab…
In practice, multiple types of distortions are associated with an image quality degradation process. The existing machine learning (ML) based image quality assessment (IQA) approaches generally established a unified model for all distortion types, or each model is trained independently for each dist…
In this paper, we propose multimodal convolutional neural networks (m-CNNs) for matching image and sentence. Our m-CNN provides an end-to-end framework with convolutional architectures to exploit image representation, word composition, and the matching relations between the two modalities. More spec…
It is desirable to combine multiple feature descriptors to improve the visual tracking performance because different features can provide complementary information to describe objects of interest. However, how to effectively fuse multiple features remains a challenging problem in visual tracking, es…