Jinyu Yang

Jinyu Yang, Mingqi Gao, Zhe Li et al.

Recently, the Segment Anything Model (SAM) gains lots of attention rapidly due to its impressive segmentation performance on images. Regarding its strong ability on image segmentation and high interactivity with different prompts, we found that it performs poorly on consistent segmentation in videos. Therefore, in this report, we propose Track Anything Model (TAM), which achieves high-performance interactive tracking and segmentation in videos. To be detailed, given a video sequence, only with very little human participation, i.e., several clicks, people can track anything they are interested in, and get satisfactory results in one-pass inference. Without additional training, such an interactive design performs impressively on video object tracking and segmentation. All resources are available on {https://github.com/gaomingqi/Track-Anything}. We hope this work can facilitate related research.

Jinyu Yang, Zhe Li, Feng Zheng et al.

Multi-modal tracking gains attention due to its ability to be more accurate and robust in complex scenarios compared to traditional RGB-based tracking. Its key lies in how to fuse multi-modal data and reduce the gap between modalities. However, multi-modal tracking still severely suffers from data deficiency, thus resulting in the insufficient learning of fusion modules. Instead of building such a fusion module, in this paper, we provide a new perspective on multi-modal tracking by attaching importance to the multi-modal visual prompts. We design a novel multi-modal prompt tracker (ProTrack), which can transfer the multi-modal inputs to a single modality by the prompt paradigm. By best employing the tracking ability of pre-trained RGB trackers learning at scale, our ProTrack can achieve high-performance multi-modal tracking by only altering the inputs, even without any extra training on multi-modal data. Extensive experiments on 5 benchmark datasets demonstrate the effectiveness of the proposed ProTrack.

Jinyu Yang, Zhe Li, Song Yan et al.

RGBD object tracking is gaining momentum in computer vision research thanks to the development of depth sensors. Although numerous RGBD trackers have been proposed with promising performance, an in-depth review for comprehensive understanding of this area is lacking. In this paper, we firstly review RGBD object trackers from different perspectives, including RGBD fusion, depth usage, and tracking framework. Then, we summarize the existing datasets and the evaluation metrics. We benchmark a representative set of RGBD trackers, and give detailed analyses based on their performances. Particularly, we are the first to provide depth quality evaluation and analysis of tracking results in depth-friendly scenarios in RGBD tracking. For long-term settings in most RGBD tracking videos, we give an analysis of trackers' performance on handling target disappearance. To enable better understanding of RGBD trackers, we propose robustness evaluation against input perturbations. Finally, we summarize the challenges and provide open directions for this community. All resources are publicly available at https://github.com/memoryunreal/RGBD-tracking-review.

Shang Gao, Jinyu Yang, Zhe Li et al.

With the development of depth sensors in recent years, RGBD object tracking has received significant attention. Compared with the traditional RGB object tracking, the addition of the depth modality can effectively solve the target and background interference. However, some existing RGBD trackers use the two modalities separately and thus some particularly useful shared information between them is ignored. On the other hand, some methods attempt to fuse the two modalities by treating them equally, resulting in the missing of modality-specific features. To tackle these limitations, we propose a novel Dual-fused Modality-aware Tracker (termed DMTracker) which aims to learn informative and discriminative representations of the target objects for robust RGBD tracking. The first fusion module focuses on extracting the shared information between modalities based on cross-modal attention. The second aims at integrating the RGB-specific and depth-specific information to enhance the fused features. By fusing both the modality-shared and modality-specific information in a modality-aware scheme, our DMTracker can learn discriminative representations in complex tracking scenes. Experiments show that our proposed tracker achieves very promising results on challenging RGBD benchmarks.

Jinyu Yang, Cheng Yang, Junze Chen et al.

Relational databases (RDBs) remain the cornerstone of modern data systems and support diverse predictive tasks. Recent relational deep learning (RDL) methods enable end-to-end prediction by converting RDBs into graphs, where rows are represented as nodes and inter-table interactions are represented as edges, and then applying graph-based models for representation learning. Despite the strong capability of RDL, effective self-supervised pre-training for RDBs remains non-trivial. RDB tasks often require multi-faceted information across different perspectives and granularities. For example, user churn classification may rely more on interaction patterns, whereas consumption value prediction requires both user-item behaviors and intrinsic user attributes for fine-grained regression. Such heterogeneous needs challenge RDB representation learning, as pre-training objectives should cover comprehensive information for downstream adaptation. However, existing SSL methods typically derive supervision from a single facet, such as node-level intrinsic attributes or subgraph-level relational structures, providing limited adaptability. To this end, we propose RelPrism, a multi-faceted self-supervised learning framework for RDBs. RelPrism constructs intrinsic, relational, and hybrid attributes from distinct perspectives, and applies multi-granularity clustering to each perspective to form corresponding pseudo-task pools. Pre-training over these pools exposes representations to broader perspectives and granularity levels, yielding a stronger basis for downstream adaptation. Experiments on 14 tasks across 5 real-world datasets show that RelPrism improves ROC-AUC by 4.15% for classification and reduces MAE by 10.75% for regression over state-of-the-art baselines. Our code is available at https://anonymous.4open.science/r/RelPrism.

Sirnam Swetha, Jinyu Yang, Tal Neiman et al.

Recent advancements in Multimodal Large Language Models (MLLMs) have revolutionized the field of vision-language understanding by integrating visual perception capabilities into Large Language Models (LLMs). The prevailing trend in this field involves the utilization of a vision encoder derived from vision-language contrastive learning (CL), showing expertise in capturing overall representations while facing difficulties in capturing detailed local patterns. In this work, we focus on enhancing the visual representations for MLLMs by combining high-frequency and detailed visual representations, obtained through masked image modeling (MIM), with semantically-enriched low-frequency representations captured by CL. To achieve this goal, we introduce X-Former which is a lightweight transformer module designed to exploit the complementary strengths of CL and MIM through an innovative interaction mechanism. Specifically, X-Former first bootstraps vision-language representation learning and multimodal-to-multimodal generative learning from two frozen vision encoders, i.e., CLIP-ViT (CL-based) and MAE-ViT (MIM-based). It further bootstraps vision-to-language generative learning from a frozen LLM to ensure visual features from X-Former can be interpreted by the LLM. To demonstrate the effectiveness of our approach, we assess its performance on tasks demanding detailed visual understanding. Extensive evaluations indicate that X-Former excels in visual reasoning tasks involving both structural and semantic categories in the GQA dataset. Assessment on fine-grained visual perception benchmark further confirms its superior capabilities in visual understanding.

Liqiong Wang, Teng Jin, Jinyu Yang et al.

In the general domain, large multimodal models (LMMs) have achieved significant advancements, yet challenges persist in applying them to specific fields, especially agriculture. As the backbone of the global economy, agriculture confronts numerous challenges, with pests and diseases being particularly concerning due to their complexity, variability, rapid spread, and high resistance. This paper specifically addresses these issues. We construct the first multimodal instruction-following dataset in the agricultural domain, covering over 221 types of pests and diseases with approximately 400,000 data entries. This dataset aims to explore and address the unique challenges in pest and disease control. Based on this dataset, we propose a knowledge-infused training method to develop Agri-LLaVA, an agricultural multimodal conversation system. To accelerate progress in this field and inspire more researchers to engage, we design a diverse and challenging evaluation benchmark for agricultural pests and diseases. Experimental results demonstrate that Agri-LLaVA excels in agricultural multimodal conversation and visual understanding, providing new insights and approaches to address agricultural pests and diseases. By open-sourcing our dataset and model, we aim to promote research and development in LMMs within the agricultural domain and make significant contributions to tackle the challenges of agricultural pests and diseases. All resources can be found at https://github.com/Kki2Eve/Agri-LLaVA.

Jinqi Luo, Jinyu Yang, Tal Neiman et al.

Multimodal Large Language Models (MLLMs) have been shown to be vulnerable to malicious queries that can elicit unsafe responses. Recent work uses prompt engineering, response classification, or finetuning to improve MLLM safety. Nevertheless, such approaches are often ineffective against evolving malicious patterns, may require rerunning the query, or demand heavy computational resources. Steering the activations of a frozen model at inference time has recently emerged as a flexible and effective solution. However, existing steering methods for MLLMs typically handle only a narrow set of safety-related concepts or struggle to adjust specific concepts without affecting others. To address these challenges, we introduce Dictionary-Aligned Concept Control (DACO), a framework that utilizes a curated concept dictionary and a Sparse Autoencoder (SAE) to provide granular control over MLLM activations. First, we curate a dictionary of 15,000 multimodal concepts by retrieving over 400,000 caption-image stimuli and summarizing their activations into concept directions. We name the dataset DACO-400K. Second, we show that the curated dictionary can be used to intervene activations via sparse coding. Third, we propose a new steering approach that uses our dictionary to initialize the training of an SAE and automatically annotate the semantics of the SAE atoms for safeguarding MLLMs. Experiments on multiple MLLMs (e.g., QwenVL, LLaVA, InternVL) across safety benchmarks (e.g., MM-SafetyBench, JailBreakV) show that DACO significantly improves MLLM safety while maintaining general-purpose capabilities.

Xiangchen Wang, Weiye Zhu, Teng Wang et al.

Recent navigation systems achieve strong benchmark results, yet real-world deployment often remains visibly stop-and-go. This bottleneck arises because the sense-inference-execution loop is still blocking: after each new observation, the controller must wait for sensing, transmission, and inference before motion can continue. Reducing action-generation cost alone therefore does not remove redundant waiting. To address this issue, we present LiveVLN, a training-free framework for more continuous embodied navigation by augmenting pretrained VLM navigators with multi-step action continuation. Instead of pausing for each full sense-and-inference round, LiveVLN overlaps execution with the processing of newly arrived observations, allowing refreshed future actions to be handed off before the current executable prefix is exhausted. This design keeps actions continuously available during motion, reducing idle waiting and enabling smoother online execution. The framework operates at runtime and can be integrated with compatible pretrained VLM navigators. Across R2R and RxR, LiveVLN preserves benchmark performance while reducing waiting time and improving action availability. In real-world deployments, it cuts average episode waiting time by up to $77.7\%$ and shortens wall-clock episode time by $12.6\%$ on StreamVLN and $19.6\%$ on NaVIDA, yielding more coherent execution during deployment. Code is available at https://github.com/NIneeeeeem/LiveVLN.

Jinyu Yang, Qingwei Wang, Feng Zheng et al.

Camouflaged Object Detection (COD) aims to detect objects with camouflaged properties. Although previous studies have focused on natural (animals and insects) and unnatural (artistic and synthetic) camouflage detection, plant camouflage has been neglected. However, plant camouflage plays a vital role in natural camouflage. Therefore, this paper introduces a new challenging problem of Plant Camouflage Detection (PCD). To address this problem, we introduce the PlantCamo dataset, which comprises 1,250 images with camouflaged plants representing 58 object categories in various natural scenes. To investigate the current status of plant camouflage detection, we conduct a large-scale benchmark study using 20+ cutting-edge COD models on the proposed dataset. Due to the unique characteristics of plant camouflage, including holes and irregular borders, we developed a new framework, named PCNet, dedicated to PCD. Our PCNet surpasses performance thanks to its multi-scale global feature enhancement and refinement. Finally, we discuss the potential applications and insights, hoping this work fills the gap in fine-grained COD research and facilitates further intelligent ecology research. All resources will be available on https://github.com/yjybuaa/PlantCamo.

Yixuan Yang, Zhen Luo, Tongsheng Ding et al.

Automatic indoor layout generation has attracted increasing attention due to its potential in interior design, virtual environment construction, and embodied AI. Existing methods fall into two categories: prompt-driven approaches that leverage proprietary LLM services (e.g., GPT APIs) and learning-based methods trained on layout data upon diffusion-based models. Prompt-driven methods often suffer from spatial inconsistency and high computational costs, while learning-based methods are typically constrained by coarse relational graphs and limited datasets, restricting their generalization to diverse room categories. In this paper, we revisit LLM-based indoor layout generation and present 3D-SynthPlace, a large-scale dataset that combines synthetic layouts generated via a 'GPT synthesize, Human inspect' pipeline, upgraded from the 3D-Front dataset. 3D-SynthPlace contains nearly 17,000 scenes, covering four common room types -- bedroom, living room, kitchen, and bathroom -- enriched with diverse objects and high-level spatial annotations. We further introduce OptiScene, a strong open-source LLM optimized for indoor layout generation, fine-tuned based on our 3D-SynthPlace dataset through our two-stage training. For the warum-up stage I, we adopt supervised fine-tuning (SFT), which is taught to first generate high-level spatial descriptions then conditionally predict concrete object placements. For the reinforcing stage II, to better align the generated layouts with human design preferences, we apply multi-turn direct preference optimization (DPO), which significantly improving layout quality and generation success rates. Extensive experiments demonstrate that OptiScene outperforms traditional prompt-driven and learning-based baselines. Moreover, OptiScene shows promising potential in interactive tasks such as scene editing and robot navigation.

Mingqi Gao, Jinyu Yang, Jingnan Luo et al.

Referring video object segmentation (RVOS) has recently generated great popularity in computer vision due to its widespread applications. Existing RVOS setting contains elaborately trimmed videos, with text-referred objects always appearing in all frames, which however fail to fully reflect the realistic challenges of this task. This simplified setting requires RVOS methods to only predict where objects, with no need to show when the objects appear. In this work, we introduce a new setting towards in-the-wild RVOS. To this end, we collect a new benchmark dataset using Youtube Untrimmed videos for RVOS - YoURVOS, which contains 1,120 in-the-wild videos with 7 times more duration and scenes than existing datasets. Our new benchmark challenges RVOS methods to show not only where but also when objects appear in videos. To set a baseline, we propose Object-level Multimodal TransFormers (OMFormer) to tackle the challenges, which are characterized by encoding object-level multimodal interactions for efficient and global spatial-temporal localisation. We demonstrate that previous VOS methods struggle on our YoURVOS benchmark, especially with the increase of target-absent frames, while our OMFormer consistently performs well. Our YoURVOS dataset offers an imperative benchmark, which will push forward the advancement of RVOS methods for practical applications.

Xusen Hei, Jiali Chen, Jinyu Yang et al.

As multimodal large language models (MLLMs) frequently exhibit errors in complex video reasoning scenarios, correcting these errors is critical for uncovering their weaknesses and improving performance. However, existing benchmarks lack systematic evaluation of MLLMs' ability to identify and correct these video reasoning errors. To bridge this gap, we propose \textit{ViRectify}, a comprehensive benchmark to evaluate their fine-grained correction capability. Through an AI-assisted annotation pipeline with human verification, we construct a dataset of over 30\textit{K} instances spanning dynamic perception, scientific reasoning, and embodied decision-making domains. In \textit{ViRectify}, we challenge MLLMs to perform step-wise error identification and generate rationales with key video evidence grounding. In addition, we further propose the trajectory evidence-driven correction framework, comprising step-wise error trajectory and reward modeling on visual evidence-grounded correction. It encourages the model to explicitly concentrate on error propagation and key timestamps for correction. Extensive evaluation across 16 advanced MLLMs demonstrates that our \textit{ViRectify} serves as a challenging testbed, where GPT-5 achieves only 31.94\% correction accuracy. Our framework enables a Qwen2.5-VL-7B to consistently outperform the variants of 72B on \textit{ViRectify}, showing the effectiveness of our approach. Further analysis uncovers systematic asymmetries in error correction across models, and our dataset is also a valuable data resource to perform reflection learning. We believe \textit{ViRectify} provides a new direction for comprehensively evaluating the advanced MLLMs in video reasoning.

Ziling Liu, Ziwei Chen, Mingqi Gao et al.

Unaligned Scene Change Detection aims to detect scene changes between image pairs captured at different times without assuming viewpoint alignment. To handle viewpoint variations, current methods rely solely on 2D visual cues to establish cross-image correspondence to assist change detection. However, large viewpoint changes can alter visual observations, causing appearance-based matching to drift or fail. Additionally, supervision limited to 2D change masks from small-scale SCD datasets restricts the learning of generalizable multi-view knowledge, making it difficult to reliably identify visual overlaps and handle occlusions. This lack of explicit geometric reasoning represents a critical yet overlooked limitation. In this work, we introduce geometric priors for the first time to address the core challenges of unaligned SCD, for reliable identification of visual overlaps, robust correspondence establishment, and explicit occlusion detection. Building on these priors, we propose a training-free framework that integrates them with the powerful representations of a visual foundation model to enable reliable change detection under viewpoint misalignment. Through extensive evaluation on the PSCD, ChangeSim, and PASLCD datasets, we demonstrate that our approach achieves superior and robust performance. Our code will be released at https://github.com/ZilingLiu/GeoSCD.

Mingqi Gao, Jingnan Luo, Jinyu Yang et al.

Motion Expression guided Video Segmentation (MeViS), as an emerging task, poses many new challenges to the field of referring video object segmentation (RVOS). In this technical report, we investigated and validated the effectiveness of static-dominant data and frame sampling on this challenging setting. Our solution achieves a J&F score of 0.5447 in the competition phase and ranks 1st in the MeViS track of the PVUW Challenge. The code is available at: https://github.com/Tapall-AI/MeViS_Track_Solution_2024.

Song Yan, Jinyu Yang, Jani Käpylä et al.

RGBD (RGB plus depth) object tracking is gaining momentum as RGBD sensors have become popular in many application fields such as robotics.However, the best RGBD trackers are extensions of the state-of-the-art deep RGB trackers. They are trained with RGB data and the depth channel is used as a sidekick for subtleties such as occlusion detection. This can be explained by the fact that there are no sufficiently large RGBD datasets to 1) train deep depth trackers and to 2) challenge RGB trackers with sequences for which the depth cue is essential. This work introduces a new RGBD tracking dataset - Depth-Track - that has twice as many sequences (200) and scene types (40) than in the largest existing dataset, and three times more objects (90). In addition, the average length of the sequences (1473), the number of deformable objects (16) and the number of annotated tracking attributes (15) have been increased. Furthermore, by running the SotA RGB and RGBD trackers on DepthTrack, we propose a new RGBD tracking baseline, namely DeT, which reveals that deep RGBD tracking indeed benefits from genuine training data. The code and dataset is available at https://github.com/xiaozai/DeT

Chunlei Liu, Wenrui Ding, Jinyu Yang et al.

Small object tracking becomes an increasingly important task, which however has been largely unexplored in computer vision. The great challenges stem from the facts that: 1) small objects show extreme vague and variable appearances, and 2) they tend to be lost easier as compared to normal-sized ones due to the shaking of lens. In this paper, we propose a novel aggregation signature suitable for small object tracking, especially aiming for the challenge of sudden and large drift. We make three-fold contributions in this work. First, technically, we propose a new descriptor, named aggregation signature, based on saliency, able to represent highly distinctive features for small objects. Second, theoretically, we prove that the proposed signature matches the foreground object more accurately with a high probability. Third, experimentally, the aggregation signature achieves a high performance on multiple datasets, outperforming the state-of-the-art methods by large margins. Moreover, we contribute with two newly collected benchmark datasets, i.e., small90 and small112, for visually small object tracking. The datasets will be available in https://github.com/bczhangbczhang/.

Chaochao Yan, Sheng Wang, Jinyu Yang et al.

Molecule generation is to design new molecules with specific chemical properties and further to optimize the desired chemical properties. Following previous work, we encode molecules into continuous vectors in the latent space and then decode the vectors into molecules under the variational autoencoder (VAE) framework. We investigate the posterior collapse problem of current RNN-based VAEs for molecule sequence generation. For the first time, we find that underestimated reconstruction loss leads to posterior collapse, and provide both theoretical and experimental evidence. We propose an effective and efficient solution to fix the problem and avoid posterior collapse. Without bells and whistles, our method achieves SOTA reconstruction accuracy and competitive validity on the ZINC 250K dataset. When generating 10,000 unique valid SMILES from random prior sampling, it costs JT-VAE1450s while our method only needs 9s. Our implementation is at https://github.com/chaoyan1037/Re-balanced-VAE.

Yongzhong Wang, Keyu Zhu, Yong Zhong et al.

The acquisition of large-scale physical interaction data, a critical prerequisite for modern robot learning, is severely bottlenecked by the prohibitive cost and scalability limits of human-in-the-loop collection paradigms. To break this barrier, we introduce Robust Autonomous Data Acquisition for Robotics (RADAR), a fully autonomous, closed-loop data generation engine that completely removes human intervention from the collection cycle. RADAR elegantly divides the cognitive load into a four-module pipeline. Anchored by 2-5 3D human demonstrations as geometric priors, a Vision-Language Model first orchestrates scene-relevant task generation via precise semantic object grounding and skill retrieval. Next, a Graph Neural Network policy translates these subtasks into physical actions via in-context imitation learning. Following execution, the VLM performs automated success evaluation using a structured Visual Question Answering pipeline. Finally, to shatter the bottleneck of manual resets, a Finite State Machine orchestrates an autonomous environment reset and asymmetric data routing mechanism. Driven by simultaneous forward-reverse planning with a strict Last-In, First-Out causal sequence, the system seamlessly restores unstructured workspaces and robustly recovers from execution failures. This continuous brain-cerebellum synergy transforms data collection into a self-sustaining process. Extensive evaluations highlight RADAR's exceptional versatility. In simulation, our framework achieves up to 90% success rates on complex, long-horizon tasks, effortlessly solving challenges where traditional baselines plummet to near-zero performance. In real-world deployments, the system reliably executes diverse, contact-rich skills (e.g., deformable object manipulation) via few-shot adaptation without domain-specific fine-tuning, providing a highly scalable paradigm for robotic data acquisition.

Xinliang Zhu, Michael Huang, Han Ding et al.

Image to image matching has been well studied in the computer vision community. Previous studies mainly focus on training a deep metric learning model matching visual patterns between the query image and gallery images. In this study, we show that pure image-to-image matching suffers from false positives caused by matching to local visual patterns. To alleviate this issue, we propose to leverage recent advances in vision-language pretraining research. Specifically, we introduce additional image-text alignment losses into deep metric learning, which serve as constraints to the image-to-image matching loss. With additional alignments between the text (e.g., product title) and image pairs, the model can learn concepts from both modalities explicitly, which avoids matching low-level visual features. We progressively develop two variants, a 3-tower and a 4-tower model, where the latter takes one more short text query input. Through extensive experiments, we show that this change leads to a substantial improvement to the image to image matching problem. We further leveraged this model for multimodal search, which takes both image and reformulation text queries to improve search quality. Both offline and online experiments show strong improvements on the main metrics. Specifically, we see 4.95% relative improvement on image matching click through rate with the 3-tower model and 1.13% further improvement from the 4-tower model.

Chuong Huynh, Jinyu Yang, Ashish Tawari et al.

Composed Image Retrieval (CIR) is a complex task that aims to retrieve images based on a multimodal query. Typical training data consists of triplets containing a reference image, a textual description of desired modifications, and the target image, which are expensive and time-consuming to acquire. The scarcity of CIR datasets has led to zero-shot approaches utilizing synthetic triplets or leveraging vision-language models (VLMs) with ubiquitous web-crawled image-caption pairs. However, these methods have significant limitations: synthetic triplets suffer from limited scale, lack of diversity, and unnatural modification text, while image-caption pairs hinder joint embedding learning of the multimodal query due to the absence of triplet data. Moreover, existing approaches struggle with complex and nuanced modification texts that demand sophisticated fusion and understanding of vision and language modalities. We present CoLLM, a one-stop framework that effectively addresses these limitations. Our approach generates triplets on-the-fly from image-caption pairs, enabling supervised training without manual annotation. We leverage Large Language Models (LLMs) to generate joint embeddings of reference images and modification texts, facilitating deeper multimodal fusion. Additionally, we introduce Multi-Text CIR (MTCIR), a large-scale dataset comprising 3.4M samples, and refine existing CIR benchmarks (CIRR and Fashion-IQ) to enhance evaluation reliability. Experimental results demonstrate that CoLLM achieves state-of-the-art performance across multiple CIR benchmarks and settings. MTCIR yields competitive results, with up to 15% performance improvement. Our refined benchmarks provide more reliable evaluation metrics for CIR models, contributing to the advancement of this important field.

Jiali Chen, Yujie Jia, Zihan Wu et al.

Experiment commentary is crucial in describing the experimental procedures, delving into underlying scientific principles, and incorporating content-related safety guidelines. In practice, human teachers rely heavily on subject-specific expertise and invest significant time preparing such commentary. To address this challenge, we introduce the task of automatic commentary generation across multi-discipline scientific experiments. While recent progress in large multimodal models (LMMs) has demonstrated promising capabilities in video understanding and reasoning, their ability to generate fine-grained and insightful experiment commentary remains largely underexplored. In this paper, we make the following contributions: (i) We construct \textit{ExpInstruct}, the first dataset tailored for experiment commentary generation, featuring over 7\textit{K} step-level commentaries across 21 scientific subjects from 3 core disciplines (\ie, science, healthcare and engineering). Each sample includes procedural descriptions along with potential scientific principles (\eg, chemical equations and physical laws) and safety guidelines. (ii) We propose ExpStar, an automatic experiment commentary generation model that leverages a retrieval-augmented mechanism to adaptively access, evaluate, and utilize external knowledge. (iii) Extensive experiments show that our ExpStar substantially outperforms 14 leading LMMs, which highlights the superiority of our dataset and model. We believe that ExpStar holds great potential for advancing AI-assisted scientific experiment instruction.

Zihao Zhao, Xinlong Zhai, Jinyu Yang et al.

Foundation models have achieved great success in natural language processing (NLP) and computer vision (CV). Their success largely stems from the ability to integrate multi-domain knowledge in pre-training and transfer it to target domains. Considering graph data, especially graphs without textual features, is ubiquitous in real-world applications such as social networks and recommendation systems, some researchers have attempted to extend this paradigm to the graph field, aiming to construct graph foundation models. However, unlike CV and NLP, there are huge gaps among the semantics and properties of graphs in different domains, while current works still adopt traditional contrastive pre-training strategies designed in the single-domain scenario, which regard contrastive samples from different domains as equivalent. From experimental investigations, we discovered that inherent domain-specific differences prevent these strategies from effectively absorbing knowledge from different domains to generate informative representations. In this paper, we propose a novel multi-domain pre-training and cross-domain transfer framework, namely MDGCL.In the pre-training stage, we design a contrastive learning strategy to substantially recognize and capture domain differences, and introduce domain tokens to encode domain-level global information. In the downstream stage, we introduce a domain attention mechanism to enable fine-grained domain knowledge transfer. Extensive experiments on five benchmark datasets have demonstrated that our method outperforms state-of-the-art significantly, with the maximum improvement of 19.33\% on accuracy and 19.13\% on Macro-F1 score.

Yixuan Yang, Jinyu Yang, Zixiang Zhao et al.

The unpaired point cloud completion task aims to complete a partial point cloud by using models trained with no ground truth. Existing unpaired point cloud completion methods are class-aware, i.e., a separate model is needed for each object class. Since they have limited generalization capabilities, these methods perform poorly in real-world scenarios when confronted with a wide range of point clouds of generic 3D objects. In this paper, we propose a novel unpaired point cloud completion framework, namely the Reference-guided Completion (RefComp) framework, which attains strong performance in both the class-aware and class-agnostic training settings. The RefComp framework transforms the unpaired completion problem into a shape translation problem, which is solved in the latent feature space of the partial point clouds. To this end, we introduce the use of partial-complete point cloud pairs, which are retrieved by using the partial point cloud to be completed as a template. These point cloud pairs are used as reference data to guide the completion process. Our RefComp framework uses a reference branch and a target branch with shared parameters for shape fusion and shape translation via a Latent Shape Fusion Module (LSFM) to enhance the structural features along the completion pipeline. Extensive experiments demonstrate that the RefComp framework achieves not only state-of-the-art performance in the class-aware training setting but also competitive results in the class-agnostic training setting on both virtual scans and real-world datasets.

Jianzheng Huang, Xianyu Mo, Ziling Liu et al.

Point tracking is becoming a powerful solver for motion estimation and video editing. Compared to classical feature matching, point tracking methods have the key advantage of robustly tracking points under complex camera motion trajectories and over extended periods. However, despite certain improvements in methodologies, current point tracking methods still struggle to track any position in video frames, especially in areas that are texture-less or weakly textured. In this work, we first introduce metrics for evaluating the texture intensity of a 3D object. Using these metrics, we classify the 3D models in ShapeNet into three levels of texture intensity and create GIFT, a challenging synthetic benchmark comprising 1800 indoor video sequences with rich annotations. Unlike existing datasets that assign ground truth points arbitrarily, GIFT precisely anchors ground truth on classified target objects, ensuring that each video corresponds to a specific texture intensity level. Furthermore, we comprehensively evaluate current methods on GIFT to assess their performance across different texture intensity levels and analyze the impact of texture on point tracking.

Henghui Ding, Chang Liu, Yunchao Wei et al.

Pixel-level Video Understanding in the Wild Challenge (PVUW) focus on complex video understanding. In this CVPR 2024 workshop, we add two new tracks, Complex Video Object Segmentation Track based on MOSE dataset and Motion Expression guided Video Segmentation track based on MeViS dataset. In the two new tracks, we provide additional videos and annotations that feature challenging elements, such as the disappearance and reappearance of objects, inconspicuous small objects, heavy occlusions, and crowded environments in MOSE. Moreover, we provide a new motion expression guided video segmentation dataset MeViS to study the natural language-guided video understanding in complex environments. These new videos, sentences, and annotations enable us to foster the development of a more comprehensive and robust pixel-level understanding of video scenes in complex environments and realistic scenarios. The MOSE challenge had 140 registered teams in total, 65 teams participated the validation phase and 12 teams made valid submissions in the final challenge phase. The MeViS challenge had 225 registered teams in total, 50 teams participated the validation phase and 5 teams made valid submissions in the final challenge phase.

Ziling Liu, Jinyu Yang, Mingqi Gao et al.

Controllable video editing has demonstrated remarkable potential across diverse applications, particularly in scenarios where capturing or re-capturing real-world videos is either impractical or costly. This paper introduces a novel and efficient system named Place-Anything, which facilitates the insertion of any object into any video solely based on a picture or text description of the target object or element. The system comprises three modules: 3D generation, video reconstruction, and 3D target insertion. This integrated approach offers an efficient and effective solution for producing and editing high-quality videos by seamlessly inserting realistic objects. Through a user study, we demonstrate that our system can effortlessly place any object into any video using just a photograph of the object. Our demo video can be found at https://youtu.be/afXqgLLRnTE. Please also visit our project page https://place-anything.github.io to get access.

Jiali Duan, Liqun Chen, Son Tran et al.

Aligning signals from different modalities is an important step in vision-language representation learning as it affects the performance of later stages such as cross-modality fusion. Since image and text typically reside in different regions of the feature space, directly aligning them at instance level is challenging especially when features are still evolving during training. In this paper, we propose to align at a higher and more stable level using cluster representation. Specifically, we treat image and text as two "views" of the same entity, and encode them into a joint vision-language coding space spanned by a dictionary of cluster centers (codebook). We contrast positive and negative samples via their cluster assignments while simultaneously optimizing the cluster centers. To further smooth out the learning process, we adopt a teacher-student distillation paradigm, where the momentum teacher of one view guides the student learning of the other. We evaluated our approach on common vision language benchmarks and obtain new SoTA on zero-shot cross modality retrieval while being competitive on various other transfer tasks.

Jinyu Yang, Jiali Duan, Son Tran et al.

Vision-language representation learning largely benefits from image-text alignment through contrastive losses (e.g., InfoNCE loss). The success of this alignment strategy is attributed to its capability in maximizing the mutual information (MI) between an image and its matched text. However, simply performing cross-modal alignment (CMA) ignores data potential within each modality, which may result in degraded representations. For instance, although CMA-based models are able to map image-text pairs close together in the embedding space, they fail to ensure that similar inputs from the same modality stay close by. This problem can get even worse when the pre-training data is noisy. In this paper, we propose triple contrastive learning (TCL) for vision-language pre-training by leveraging both cross-modal and intra-modal self-supervision. Besides CMA, TCL introduces an intra-modal contrastive objective to provide complementary benefits in representation learning. To take advantage of localized and structural information from image and text input, TCL further maximizes the average MI between local regions of image/text and their global summary. To the best of our knowledge, ours is the first work that takes into account local structure information for multi-modality representation learning. Experimental evaluations show that our approach is competitive and achieves the new state of the art on various common down-stream vision-language tasks such as image-text retrieval and visual question answering.

Song Yan, Jinyu Yang, Ales Leonardis et al.

Depth (D) indicates occlusion and is less sensitive to illumination changes, which make depth attractive modality for Visual Object Tracking (VOT). Depth is used in RGBD object tracking where the best trackers are deep RGB trackers with additional heuristic using depth maps. There are two potential reasons for the heuristics: 1) the lack of large RGBD tracking datasets to train deep RGBD trackers and 2) the long-term evaluation protocol of VOT RGBD that benefits from heuristics such as depth-based occlusion detection. In this work, we study how far D-only tracking can go if trained with large amounts of depth data. To compensate the lack of depth data, we generate depth maps for tracking. We train a "Depth-DiMP" from the scratch with the generated data and fine-tune it with the available small RGBD tracking datasets. The depth-only DiMP achieves good accuracy in depth-only tracking and combined with the original RGB DiMP the end-to-end trained RGBD-DiMP outperforms the recent VOT 2020 RGBD winners.

Jinyu Yang, Jingjing Liu, Ning Xu et al.

Unsupervised domain adaptation (UDA) aims to transfer the knowledge learnt from a labeled source domain to an unlabeled target domain. Previous work is mainly built upon convolutional neural networks (CNNs) to learn domain-invariant representations. With the recent exponential increase in applying Vision Transformer (ViT) to vision tasks, the capability of ViT in adapting cross-domain knowledge, however, remains unexplored in the literature. To fill this gap, this paper first comprehensively investigates the transferability of ViT on a variety of domain adaptation tasks. Surprisingly, ViT demonstrates superior transferability over its CNNs-based counterparts with a large margin, while the performance can be further improved by incorporating adversarial adaptation. Notwithstanding, directly using CNNs-based adaptation strategies fails to take the advantage of ViT's intrinsic merits (e.g., attention mechanism and sequential image representation) which play an important role in knowledge transfer. To remedy this, we propose an unified framework, namely Transferable Vision Transformer (TVT), to fully exploit the transferability of ViT for domain adaptation. Specifically, we delicately devise a novel and effective unit, which we term Transferability Adaption Module (TAM). By injecting learned transferabilities into attention blocks, TAM compels ViT focus on both transferable and discriminative features. Besides, we leverage discriminative clustering to enhance feature diversity and separation which are undermined during adversarial domain alignment. To verify its versatility, we perform extensive studies of TVT on four benchmarks and the experimental results demonstrate that TVT attains significant improvements compared to existing state-of-the-art UDA methods.

Jinyu Yang, Chunyuan Li, Weizhi An et al.

Recent studies imply that deep neural networks are vulnerable to adversarial examples -- inputs with a slight but intentional perturbation are incorrectly classified by the network. Such vulnerability makes it risky for some security-related applications (e.g., semantic segmentation in autonomous cars) and triggers tremendous concerns on the model reliability. For the first time, we comprehensively evaluate the robustness of existing UDA methods and propose a robust UDA approach. It is rooted in two observations: (i) the robustness of UDA methods in semantic segmentation remains unexplored, which pose a security concern in this field; and (ii) although commonly used self-supervision (e.g., rotation and jigsaw) benefits image tasks such as classification and recognition, they fail to provide the critical supervision signals that could learn discriminative representation for segmentation tasks. These observations motivate us to propose adversarial self-supervision UDA (or ASSUDA) that maximizes the agreement between clean images and their adversarial examples by a contrastive loss in the output space. Extensive empirical studies on commonly used benchmarks demonstrate that ASSUDA is resistant to adversarial attacks.

Jinyu Yang, Peilin Zhao, Yu Rong et al.

Graph Neural Networks (GNNs) draw their strength from explicitly modeling the topological information of structured data. However, existing GNNs suffer from limited capability in capturing the hierarchical graph representation which plays an important role in graph classification. In this paper, we innovatively propose hierarchical graph capsule network (HGCN) that can jointly learn node embeddings and extract graph hierarchies. Specifically, disentangled graph capsules are established by identifying heterogeneous factors underlying each node, such that their instantiation parameters represent different properties of the same entity. To learn the hierarchical representation, HGCN characterizes the part-whole relationship between lower-level capsules (part) and higher-level capsules (whole) by explicitly considering the structure information among the parts. Experimental studies demonstrate the effectiveness of HGCN and the contribution of each component.

Chaochao Yan, Qianggang Ding, Peilin Zhao et al.

Retrosynthesis is the process of recursively decomposing target molecules into available building blocks. It plays an important role in solving problems in organic synthesis planning. To automate or assist in the retrosynthesis analysis, various retrosynthesis prediction algorithms have been proposed. However, most of them are cumbersome and lack interpretability about their predictions. In this paper, we devise a novel template-free algorithm for automatic retrosynthetic expansion inspired by how chemists approach retrosynthesis prediction. Our method disassembles retrosynthesis into two steps: i) identify the potential reaction center of the target molecule through a novel graph neural network and generate intermediate synthons, and ii) generate the reactants associated with synthons via a robust reactant generation model. While outperforming the state-of-the-art baselines by a significant margin, our model also provides chemically reasonable interpretation.

Jinyu Yang, Weizhi An, Sheng Wang et al.

Unsupervised domain adaptation enables to alleviate the need for pixel-wise annotation in the semantic segmentation. One of the most common strategies is to translate images from the source domain to the target domain and then align their marginal distributions in the feature space using adversarial learning. However, source-to-target translation enlarges the bias in translated images and introduces extra computations, owing to the dominant data size of the source domain. Furthermore, consistency of the joint distribution in source and target domains cannot be guaranteed through global feature alignment. Here, we present an innovative framework, designed to mitigate the image translation bias and align cross-domain features with the same category. This is achieved by 1) performing the target-to-source translation and 2) reconstructing both source and target images from their predicted labels. Extensive experiments on adapting from synthetic to real urban scene understanding demonstrate that our framework competes favorably against existing state-of-the-art methods.

Jinyu Yang, Weizhi An, Chaochao Yan et al.

In this paper, we consider the problem of unsupervised domain adaptation in the semantic segmentation. There are two primary issues in this field, i.e., what and how to transfer domain knowledge across two domains. Existing methods mainly focus on adapting domain-invariant features (what to transfer) through adversarial learning (how to transfer). Context dependency is essential for semantic segmentation, however, its transferability is still not well understood. Furthermore, how to transfer contextual information across two domains remains unexplored. Motivated by this, we propose a cross-attention mechanism based on self-attention to capture context dependencies between two domains and adapt transferable context. To achieve this goal, we design two cross-domain attention modules to adapt context dependencies from both spatial and channel views. Specifically, the spatial attention module captures local feature dependencies between each position in the source and target image. The channel attention module models semantic dependencies between each pair of cross-domain channel maps. To adapt context dependencies, we further selectively aggregate the context information from two domains. The superiority of our method over existing state-of-the-art methods is empirically proved on "GTA5 to Cityscapes" and "SYNTHIA to Cityscapes".

Gaoyang Li, Jinyu Yang, Chunguo Wu et al.

Support vector regression (SVR) is one of the most popular machine learning algorithms aiming to generate the optimal regression curve through maximizing the minimal margin of selected training samples, i.e., support vectors. Recent researchers reveal that maximizing the margin distribution of whole training dataset rather than the minimal margin of a few support vectors, is prone to achieve better generalization performance. However, the margin distribution support vector regression machines suffer difficulties resulted from solving a non-convex quadratic optimization, compared to the margin distribution strategy for support vector classification, This paper firstly proposes a maximal margin distribution model for SVR(MMD-SVR), then implementing coupled constrain factor to convert the non-convex quadratic optimization to a convex problem with linear constrains, which enhance the training feasibility and efficiency for SVR to derived from maximizing the margin distribution. The theoretical and empirical analysis illustrates the superiority of MMD-SVR. In addition, numerical experiments show that MMD-SVR could significantly improve the accuracy of prediction and generate more smooth regression curve with better generalization compared with the classic SVR.

Jinyu Yang, Bo Zhang

This study provides a systematic review of the recent advances in designing the intelligent tutoring robot (ITR), and summarises the status quo of applying artificial intelligence (AI) techniques. We first analyse the environment of the ITR and propose a relationship model for describing interactions of ITR with the students, the social milieu and the curriculum. Then, we transform the relationship model into the perception-planning-action model for exploring what AI techniques are suitable to be applied in the ITR. This article provides insights on promoting human-robot teaching-learning process and AI-assisted educational techniques, illustrating the design guidelines and future research perspectives in intelligent tutoring robots.

Bo Zhang, Bin Chen, Jinyu Yang et al.

Motivated by Shannon's model and recent rehabilitation of self-supervised artificial intelligence having a "World Model", this paper propose an unified intelligence-communication (UIC) model for describing a single agent and any multi-agent system. Firstly, the environment is modelled as the generic communication channel between agents. Secondly, the UIC model adopts a learning-agent model for unifying several well-adopted agent architecture, e.g. rule-based agent model in complex adaptive systems, layered model for describing human-level intelligence, world-model based agent model. The model may also provide an unified approach to investigate a multi-agent system (MAS) having multiple action-perception modalities, e.g. explicitly information transfer and implicit information transfer. This treatise would be divided into three parts, and this first part provides an overview of the UIC model without introducing cumbersome mathematical analysis and optimizations. In the second part of this treatise, case studies with quantitative analysis driven by the UIC model would be provided, exemplifying the adoption of the UIC model in multi-agent system. Specifically, two representative cases would be studied, namely the analysis of a natural multi-agent system, as well as the co-design of communication, perception and action in an artificial multi-agent system. In the third part of this treatise, the paper provides further insights and future research directions motivated by the UIC model, such as unification of single intelligence and collective intelligence, a possible explanation of intelligence emergence and a dual model for agent-environment intelligence hypothesis. Notes: This paper is a Previewed Version, the extended full-version would be released after being accepted.