arXiv subjects

Zitian Wang

Publications and source records attributed to Zitian Wang.

17 recordsLinked to original sources

arXiv2026

TRACE: Temporal Retrieval with Anchored and Convergent Evidence for Long-Horizon Video Understanding

A long-video answer is evidence-supported only when the frames decoded from the video cover every event the answer depends on. Existing evaluations score final-answer correctness or predicted evidence intervals, but the frames a method decodes before answering are rarely audited, so correct answers can still rest on incomplete observation. We introduce VES-Bench, a 600-question benchmark of Temporal Ordering and Event Counting items over 348 public long videos. Each item carries a jointly necessary set of evidence intervals, letting us audit at three strictness levels whether a method's decoded frames cover every one of them. We also propose TRACE, a training-free agent that grounds answers in raw visual clips, builds an evidence bundle round by round, and stops only when the answer stabilises as the bundle grows and a final pass over the same clips returns the same answer. Under a same-backbone audit, TRACE answers 50.7% of questions correctly with at least two decoded frames inside every evidence interval, at 98.7 frames per question: over 10 points above uniform decoding at 128 frames (40.2%), and within 2.6 points of uniform decoding at 256 frames at 0.39x its frame cost, while reaching the highest answer accuracy in the audit (63.5%). TRACE also stays competitive on Video-MME (86.1), LVBench (75.6), and LongVideoBench (75.1).

cs.CV↗

arXiv2026

Revisiting the Intra-Team Communication Method to Elicit Level-k Reasoning in Beauty Contests and 11-20 Games

How level-0 players behave and how they are perceived by higher-level players are central questions in the literature on level-k models of boundedly rational strategic reasoning. To study these twin questions, we apply the intra-team communication method developed by Burchardi and Penczynski (2014) to identify level-0 actions and beliefs in the canonical beauty contest game and in a variant of the 11-20 game of Goeree et al. (2018), in which behavior appears inconsistent with the standard level-k model. In the beauty contest game, we replicate Burchardi and Penczynski (2014)'s finding that elicited level-0 beliefs align with observed level-0 actions. In the variant of the 11-20 game, however, elicited level-0 beliefs and observed level-0 actions diverge, and both depart from the standard level-0 assumption, suggesting a complementary explanation for the behavioral pattern documented by Goeree et al. (2018).

econ.GN↗

arXiv2026

SVCBench: A Streaming Video Counting Benchmark for Spatial-Temporal State Maintenance

Video understanding requires models to continuously track and update world state during playback. Although existing benchmarks have advanced video understanding evaluation across multiple dimensions, they provide limited visibility into how models maintain world state over time. We propose SVCBench, a Streaming Video Counting Benchmark that repositions counting as a minimal, controlled probe for diagnosing models' world-state maintenance capability. We decompose this capability into object counting and event counting, forming 8 fine-grained subcategories. Object counting covers tracking currently visible objects and cumulative unique identities, while event counting covers detecting instantaneous actions and tracking complete activity cycles. SVCBench contains 406 videos with frame-by-frame annotations of 10,071 event occurrences and object state changes, yielding 1,000 streaming QA pairs with 4,576 query points distributed along video timelines. By observing state maintenance trajectories through streaming multi-point queries, we design three complementary metrics to diagnose numerical precision, trajectory consistency, and temporal awareness. Evaluations of mainstream video-language models show that current models still exhibit significant deficiencies in spatial-temporal state maintenance, with especially poor performance on periodic event counting. SVCBench provides a diagnostic framework for measuring and improving state maintenance in video understanding systems. Our code and data are available at https://buaa-colalab.github.io/SVCBench.

cs.CV↗

arXiv2025

WeThink: Toward General-purpose Vision-Language Reasoning via Reinforcement Learning

Building on the success of text-based reasoning models like DeepSeek-R1, extending these capabilities to multimodal reasoning holds great promise. While recent works have attempted to adapt DeepSeek-R1-style reinforcement learning (RL) training paradigms to multimodal large language models (MLLM), focusing on domain-specific tasks like math and visual perception, a critical question remains: How can we achieve the general-purpose visual-language reasoning through RL? To address this challenge, we make three key efforts: (1) A novel Scalable Multimodal QA Synthesis pipeline that autonomously generates context-aware, reasoning-centric question-answer (QA) pairs directly from the given images. (2) The open-source WeThink dataset containing over 120K multimodal QA pairs with annotated reasoning paths, curated from 18 diverse dataset sources and covering various question domains. (3) A comprehensive exploration of RL on our dataset, incorporating a hybrid reward mechanism that combines rule-based verification with model-based assessment to optimize RL training efficiency across various task domains. Across 14 diverse MLLM benchmarks, we demonstrate that our WeThink dataset significantly enhances performance, from mathematical reasoning to diverse general multimodal tasks. Moreover, we show that our automated data pipeline can continuously increase data diversity to further improve model performance.

cs.CV↗

arXiv2025

Instruction-Oriented Preference Alignment for Enhancing Multi-Modal Comprehension Capability of MLLMs

Preference alignment has emerged as an effective strategy to enhance the performance of Multimodal Large Language Models (MLLMs) following supervised fine-tuning. While existing preference alignment methods predominantly target hallucination factors, they overlook the factors essential for multi-modal comprehension capabilities, often narrowing their improvements on hallucination mitigation. To bridge this gap, we propose Instruction-oriented Preference Alignment (IPA), a scalable framework designed to automatically construct alignment preferences grounded in instruction fulfillment efficacy. Our method involves an automated preference construction coupled with a dedicated verification process that identifies instruction-oriented factors, avoiding significant variability in response representations. Additionally, IPA incorporates a progressive preference collection pipeline, further recalling challenging samples through model self-evolution and reference-guided refinement. Experiments conducted on Qwen2VL-7B demonstrate IPA's effectiveness across multiple benchmarks, including hallucination evaluation, visual question answering, and text understanding tasks, highlighting its capability to enhance general comprehension.

cs.CV↗

arXiv2024

Treat Stillness with Movement: Remote Sensing Change Detection via Coarse-grained Temporal Foregrounds Mining

Current works focus on addressing the remote sensing change detection task using bi-temporal images. Although good performance can be achieved, however, seldom of they consider the motion cues which may also be vital. In this work, we revisit the widely adopted bi-temporal images-based framework and propose a novel Coarse-grained Temporal Mining Augmented (CTMA) framework. To be specific, given the bi-temporal images, we first transform them into a video using interpolation operations. Then, a set of temporal encoders is adopted to extract the motion features from the obtained video for coarse-grained changed region prediction. Subsequently, we design a novel Coarse-grained Foregrounds Augmented Spatial Encoder module to integrate both global and local information. We also introduce a motion augmented strategy that leverages motion cues as an additional output to aggregate with the spatial features for improved results. Meanwhile, we feed the input image pairs into the ResNet to get the different features and also the spatial blocks for fine-grained feature learning. More importantly, we propose a mask augmented strategy that utilizes coarse-grained changed regions, incorporating them into the decoder blocks to enhance the final changed prediction. Extensive experiments conducted on multiple benchmark datasets fully validated the effectiveness of our proposed framework for remote sensing image change detection. The source code of this paper will be released on https://github.com/Event-AHU/CTM_Remote_Sensing_Change_Detection

cs.CV↗

arXiv2024

MV2DFusion: Leveraging Modality-Specific Object Semantics for Multi-Modal 3D Detection

The rise of autonomous vehicles has significantly increased the demand for robust 3D object detection systems. While cameras and LiDAR sensors each offer unique advantages--cameras provide rich texture information and LiDAR offers precise 3D spatial data--relying on a single modality often leads to performance limitations. This paper introduces MV2DFusion, a multi-modal detection framework that integrates the strengths of both worlds through an advanced query-based fusion mechanism. By introducing an image query generator to align with image-specific attributes and a point cloud query generator, MV2DFusion effectively combines modality-specific object semantics without biasing toward one single modality. Then the sparse fusion process can be accomplished based on the valuable object semantics, ensuring efficient and accurate object detection across various scenarios. Our framework's flexibility allows it to integrate with any image and point cloud-based detectors, showcasing its adaptability and potential for future advancements. Extensive evaluations on the nuScenes and Argoverse2 datasets demonstrate that MV2DFusion achieves state-of-the-art performance, particularly excelling in long-range detection scenarios.

cs.CV↗

arXiv2024

Enhancing 3D Lane Detection and Topology Reasoning with 2D Lane Priors

3D lane detection and topology reasoning are essential tasks in autonomous driving scenarios, requiring not only detecting the accurate 3D coordinates on lane lines, but also reasoning the relationship between lanes and traffic elements. Current vision-based methods, whether explicitly constructing BEV features or not, all establish the lane anchors/queries in 3D space while ignoring the 2D lane priors. In this study, we propose Topo2D, a novel framework based on Transformer, leveraging 2D lane instances to initialize 3D queries and 3D positional embeddings. Furthermore, we explicitly incorporate 2D lane features into the recognition of topology relationships among lane centerlines and between lane centerlines and traffic elements. Topo2D achieves 44.5% OLS on multi-view topology reasoning benchmark OpenLane-V2 and 62.6% F-Socre on single-view 3D lane detection benchmark OpenLane, exceeding the performance of existing state-of-the-art methods.

cs.CV↗

arXiv2024

Eliminating Cross-modal Conflicts in BEV Space for LiDAR-Camera 3D Object Detection

Recent 3D object detectors typically utilize multi-sensor data and unify multi-modal features in the shared bird's-eye view (BEV) representation space. However, our empirical findings indicate that previous methods have limitations in generating fusion BEV features free from cross-modal conflicts. These conflicts encompass extrinsic conflicts caused by BEV feature construction and inherent conflicts stemming from heterogeneous sensor signals. Therefore, we propose a novel Eliminating Conflicts Fusion (ECFusion) method to explicitly eliminate the extrinsic/inherent conflicts in BEV space and produce improved multi-modal BEV features. Specifically, we devise a Semantic-guided Flow-based Alignment (SFA) module to resolve extrinsic conflicts via unifying spatial distribution in BEV space before fusion. Moreover, we design a Dissolved Query Recovering (DQR) mechanism to remedy inherent conflicts by preserving objectness clues that are lost in the fusion BEV feature. In general, our method maximizes the effective information utilization of each modality and leverages inter-modal complementarity. Our method achieves state-of-the-art performance in the highly competitive nuScenes 3D object detection dataset. The code is released at https://github.com/fjhzhixi/ECFusion.

cs.CV↗

arXiv2023

Object as Query: Lifting any 2D Object Detector to 3D Detection

3D object detection from multi-view images has drawn much attention over the past few years. Existing methods mainly establish 3D representations from multi-view images and adopt a dense detection head for object detection, or employ object queries distributed in 3D space to localize objects. In this paper, we design Multi-View 2D Objects guided 3D Object Detector (MV2D), which can lift any 2D object detector to multi-view 3D object detection. Since 2D detections can provide valuable priors for object existence, MV2D exploits 2D detectors to generate object queries conditioned on the rich image semantics. These dynamically generated queries help MV2D to recall objects in the field of view and show a strong capability of localizing 3D objects. For the generated queries, we design a sparse cross attention module to force them to focus on the features of specific objects, which suppresses interference from noises. The evaluation results on the nuScenes dataset demonstrate the dynamic object queries and sparse feature aggregation can promote 3D detection capability. MV2D also exhibits a state-of-the-art performance among existing methods. We hope MV2D can serve as a new baseline for future research. Code is available at \url{https://github.com/tusen-ai/MV2D}.

cs.CV↗

arXiv2023

VcT: Visual change Transformer for Remote Sensing Image Change Detection

Existing visual change detectors usually adopt CNNs or Transformers for feature representation learning and focus on learning effective representation for the changed regions between images. Although good performance can be obtained by enhancing the features of the change regions, however, these works are still limited mainly due to the ignorance of mining the unchanged background context information. It is known that one main challenge for change detection is how to obtain the consistent representations for two images involving different variations, such as spatial variation, sunlight intensity, etc. In this work, we demonstrate that carefully mining the common background information provides an important cue to learn the consistent representations for the two images which thus obviously facilitates the visual change detection problem. Based on this observation, we propose a novel Visual change Transformer (VcT) model for visual change detection problem. To be specific, a shared backbone network is first used to extract the feature maps for the given image pair. Then, each pixel of feature map is regarded as a graph node and the graph neural network is proposed to model the structured information for coarse change map prediction. Top-K reliable tokens can be mined from the map and refined by using the clustering algorithm. Then, these reliable tokens are enhanced by first utilizing self/cross-attention schemes and then interacting with original features via an anchor-primary attention learning module. Finally, the prediction head is proposed to get a more accurate change map. Extensive experiments on multiple benchmark datasets validated the effectiveness of our proposed VcT model.

cs.CV↗

arXiv2022

Multi-view Human Body Mesh Translator

Existing methods for human mesh recovery mainly focus on single-view frameworks, but they often fail to produce accurate results due to the ill-posed setup. Considering the maturity of the multi-view motion capture system, in this paper, we propose to solve the prior ill-posed problem by leveraging multiple images from different views, thus significantly enhancing the quality of recovered meshes. In particular, we present a novel \textbf{M}ulti-view human body \textbf{M}esh \textbf{T}ranslator (MMT) model for estimating human body mesh with the help of vision transformer. Specifically, MMT takes multi-view images as input and translates them to targeted meshes in a single-forward manner. MMT fuses features of different views in both encoding and decoding phases, leading to representations embedded with global information. Additionally, to ensure the tokens are intensively focused on the human pose and shape, MMT conducts cross-view alignment at the feature level by projecting 3D keypoint positions to each view and enforcing their consistency in geometry constraints. Comprehensive experiments demonstrate that MMT outperforms existing single or multi-view models by a large margin for human mesh recovery task, notably, 28.8\% improvement in MPVE over the current state-of-the-art method on the challenging HUMBI dataset. Qualitative evaluation also verifies the effectiveness of MMT in reconstructing high-quality human mesh. Codes will be made available upon acceptance.

cs.CV↗

arXiv2022

Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation

In this paper, we present a novel Distribution-Aware Single-stage (DAS) model for tackling the challenging multi-person 3D pose estimation problem. Different from existing top-down and bottom-up methods, the proposed DAS model simultaneously localizes person positions and their corresponding body joints in the 3D camera space in a one-pass manner. This leads to a simplified pipeline with enhanced efficiency. In addition, DAS learns the true distribution of body joints for the regression of their positions, rather than making a simple Laplacian or Gaussian assumption as previous works. This provides valuable priors for model prediction and thus boosts the regression-based scheme to achieve competitive performance with volumetric-base ones. Moreover, DAS exploits a recursive update strategy for progressively approaching to regression target, alleviating the optimization difficulty and further lifting the regression performance. DAS is implemented with a fully Convolutional Neural Network and end-to-end learnable. Comprehensive experiments on benchmarks CMU Panoptic and MuPoTS-3D demonstrate the superior efficiency of the proposed DAS model, specifically 1.5x speedup over previous best model, and its stat-of-the-art accuracy for multi-person 3D pose estimation.

cs.CV↗

arXiv2021

Lvio-Fusion: A Self-adaptive Multi-sensor Fusion SLAM Framework Using Actor-critic Method

State estimation with sensors is essential for mobile robots. Due to different performance of sensors in different environments, how to fuse measurements of various sensors is a problem. In this paper, we propose a tightly coupled multi-sensor fusion framework, Lvio-Fusion, which fuses stereo camera, Lidar, IMU, and GPS based on the graph optimization. Especially for urban traffic scenes, we introduce a segmented global pose graph optimization with GPS and loop-closure, which can eliminate accumulated drifts. Additionally, we creatively use a actor-critic method in reinforcement learning to adaptively adjust sensors' weight. After training, actor-critic agent can provide the system better and dynamic sensors' weight. We evaluate the performance of our system on public datasets and compare it with other state-of-the-art methods, which shows that the proposed method achieves high estimation accuracy and robustness to various environments. And our implementations are open source and highly scalable.

cs.RO↗

arXiv2021

Human-centric Relation Segmentation: Dataset and Solution

Vision and language understanding techniques have achieved remarkable progress, but currently it is still difficult to well handle problems involving very fine-grained details. For example, when the robot is told to "bring me the book in the girl's left hand", most existing methods would fail if the girl holds one book respectively in her left and right hand. In this work, we introduce a new task named human-centric relation segmentation (HRS), as a fine-grained case of HOI-det. HRS aims to predict the relations between the human and surrounding entities and identify the relation-correlated human parts, which are represented as pixel-level masks. For the above exemplar case, our HRS task produces results in the form of relation triplets and exacts segmentation masks of the book, with which the robot can easily accomplish the grabbing task. Correspondingly, we collect a new Person In Context (PIC) dataset for this new task, which contains 17,122 high-resolution images and densely annotated entity segmentation and relations, including 141 object categories, 23 relation categories and 25 semantic human parts. We also propose a Simultaneous Matching and Segmentation (SMS) framework as a solution to the HRS task. I Outputs of the three branches are fused to produce the final HRS results. Extensive experiments on PIC and V-COCO datasets show that the proposed SMS method outperforms baselines with the 36 FPS inference speed.

cs.CV↗

arXiv2019

Decoupled molecular and inorganic framework dynamics in CH$_3$NH$_3$PbCl$_3$

The organic-inorganic lead halide perovskites are composed of organic molecules imbedded in an inorganic framework. The compounds with general formula CH$_{3}$NH$_{3}$PbX$_{3}$ (MAPbX$_{2}$) display large photovoltaic efficiencies for halogens $X$=Cl, Br, and I in a wide variety of sample geometries and preparation methods. The organic cation and inorganic framework are bound by hydrogen bonds that tether the molecules to the halide anions, and this has been suggested to be important to the optoelectronic properties. We have studied the effects of this bonding using time-of-flight neutron spectroscopy to measure the molecular dynamics in CH$_3$NH$_3$PbCl$_3$ (MAPbCl$_3$). Low-energy/high-resolution neutron backscattering reveals thermally-activated molecular dynamics with a characteristic temperature of $\sim$ 95\,K. At this same temperature, higher-energy neutron spectroscopy indicates the presence of an anomalous broadening in energy (reduced lifetime) associated with the molecular vibrations. By contrast, neutron powder diffraction shows that a spatially long-range structural phase transitions occurs at 178\,K (cubic $\rightarrow$ tetragonal) and 173\,K (tetragonal $\rightarrow$ orthorhombic). The large difference between these two temperature scales suggests that the molecular and inorganic lattice dynamics in MAPbCl$_3$ are actually decoupled. With the assumption that underlying physical mechanisms do not change with differing halogens in the organic-inorganic perovskites, we speculate that the energy scale most relevant to the photovoltaic properties of the lead-halogen perovskites is set by the lead-halide bond, not by the hydrogen bond.

cond-mat.mtrl-sci↗

arXiv2017

Joint and Competitive Caching Designs in Large-Scale Multi-Tier Wireless Multicasting Networks

Caching and multicasting are two promising methods to support massive content delivery in multi-tier wireless networks. In this paper, we consider a random caching and multicasting scheme with caching distributions in the two tiers as design parameters, to achieve efficient content dissemination in a two-tier large-scale cache-enabled wireless multicasting network. First, we derive tractable expressions for the successful transmission probabilities in the general region as well as the high SNR and high user density region, respectively, utilizing tools from stochastic geometry. Then, for the case of a single operator for the two tiers, we formulate the optimal joint caching design problem to maximize the successful transmission probability in the asymptotic region, which is nonconvex in general. By using the block successive approximate optimization technique, we develop an iterative algorithm, which is shown to converge to a stationary point. Next, for the case of two different operators, one for each tier, we formulate the competitive caching design game where each tier maximizes its successful transmission probability in the asymptotic region. We show that the game has a unique Nash equilibrium (NE) and develop an iterative algorithm, which is shown to converge to the NE under a mild condition. Finally, by numerical simulations, we show that the proposed designs achieve significant gains over existing schemes.

cs.IT↗