arXiv subjects

Hongyuan Zhu

Publications and source records attributed to Hongyuan Zhu.

At least 37 records · Page 2Linked to original sources

arXiv2025

Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning

We introduce Ego-R1, a novel framework for reasoning over ultra-long (i.e., in days and weeks) egocentric videos, which leverages a structured Chain-of-Tool-Thought (CoTT) process, orchestrated by an Ego-R1 Agent trained via reinforcement learning (RL). Inspired by human problem-solving strategies, CoTT decomposes complex reasoning into modular steps, with the RL agent invoking specific tools, one per step, to iteratively and collaboratively answer sub-questions tackling such tasks as temporal retrieval and multi-modal understanding. We design a two-stage training paradigm involving supervised finetuning (SFT) of a pretrained language model using CoTT data and RL to enable our agent to dynamically propose step-by-step tools for long-range reasoning. To facilitate training, we construct a dataset called Ego-R1 Data, which consists of Ego-CoTT-25K for SFT and Ego-QA-4.4K for RL. Furthermore, our Ego-R1 agent is evaluated on a newly curated week-long video QA benchmark, Ego-R1 Bench, which contains human-verified QA pairs from hybrid sources. Extensive results demonstrate that the dynamic, tool-augmented chain-of-thought reasoning by our Ego-R1 Agent can effectively tackle the unique challenges of understanding ultra-long egocentric videos, significantly extending the time coverage from few hours to a week.

cs.CV↗

arXiv2025

PointCloud-Text Matching: Benchmark Datasets and a Baseline

In this paper, we present and study a new instance-level retrieval task: PointCloud-Text Matching (PTM), which aims to identify the exact cross-modal instance that matches a given point-cloud query or text query. PTM has potential applications in various scenarios, such as indoor/urban-canyon localization and scene retrieval. However, there is a lack of suitable and targeted datasets for PTM in practice. To address this issue, we present a new PTM benchmark dataset, namely SceneDepict-3D2T. We observe that the data poses significant challenges due to its inherent characteristics, such as the sparsity, noise, or disorder of point clouds and the ambiguity, vagueness, or incompleteness of texts, which render existing cross-modal matching methods ineffective for PTM. To overcome these challenges, we propose a PTM baseline, named Robust PointCloud-Text Matching method (RoMa). RoMa consists of two key modules: a Dual Attention Perception module (DAP) and a Robust Negative Contrastive Learning module (RNCL). Specifically, DAP leverages token-level and feature-level attention mechanisms to adaptively focus on useful local and global features, and aggregate them into common representations, thereby reducing the adverse impact of noise and ambiguity. To handle noisy correspondence, RNCL enhances robustness against mismatching by dividing negative pairs into clean and noisy subsets and assigning them forward and reverse optimization directions, respectively. We conduct extensive experiments on our benchmarks and demonstrate the superiority of our RoMa.

cs.CV↗

arXiv2024

Contributing Dimension Structure of Deep Feature for Coreset Selection

Coreset selection seeks to choose a subset of crucial training samples for efficient learning. It has gained traction in deep learning, particularly with the surge in training dataset sizes. Sample selection hinges on two main aspects: a sample's representation in enhancing performance and the role of sample diversity in averting overfitting. Existing methods typically measure both the representation and diversity of data based on similarity metrics, such as L2-norm. They have capably tackled representation via distribution matching guided by the similarities of features, gradients, or other information between data. However, the results of effectively diverse sample selection are mired in sub-optimality. This is because the similarity metrics usually simply aggregate dimension similarities without acknowledging disparities among the dimensions that significantly contribute to the final similarity. As a result, they fall short of adequately capturing diversity. To address this, we propose a feature-based diversity constraint, compelling the chosen subset to exhibit maximum diversity. Our key lies in the introduction of a novel Contributing Dimension Structure (CDS) metric. Different from similarity metrics that measure the overall similarity of high-dimensional features, our CDS metric considers not only the reduction of redundancy in feature dimensions, but also the difference between dimensions that contribute significantly to the final similarity. We reveal that existing methods tend to favor samples with similar CDS, leading to a reduced variety of CDS types within the coreset and subsequently hindering model performance. In response, we enhance the performance of five classical selection methods by integrating the CDS constraint. Our experiments on three datasets demonstrate the general effectiveness of the proposed method in boosting existing methods.

cs.LG↗

arXiv2024

Direct Distillation between Different Domains

Knowledge Distillation (KD) aims to learn a compact student network using knowledge from a large pre-trained teacher network, where both networks are trained on data from the same distribution. However, in practical applications, the student network may be required to perform in a new scenario (i.e., the target domain), which usually exhibits significant differences from the known scenario of the teacher network (i.e., the source domain). The traditional domain adaptation techniques can be integrated with KD in a two-stage process to bridge the domain gap, but the ultimate reliability of two-stage approaches tends to be limited due to the high computational consumption and the additional errors accumulated from both stages. To solve this problem, we propose a new one-stage method dubbed ``Direct Distillation between Different Domains" (4Ds). We first design a learnable adapter based on the Fourier transform to separate the domain-invariant knowledge from the domain-specific knowledge. Then, we build a fusion-activation mechanism to transfer the valuable domain-invariant knowledge to the student network, while simultaneously encouraging the adapter within the teacher network to learn the domain-specific knowledge of the target data. As a result, the teacher network can effectively transfer categorical knowledge that aligns with the target domain of the student network. Intensive experiments on various benchmark datasets demonstrate that our proposed 4Ds method successfully produces reliable student networks and outperforms state-of-the-art approaches.

cs.LG↗

arXiv2023

M3DBench: Let's Instruct Large Models with Multi-modal 3D Prompts

Recently, 3D understanding has become popular to facilitate autonomous agents to perform further decisionmaking. However, existing 3D datasets and methods are often limited to specific tasks. On the other hand, recent progress in Large Language Models (LLMs) and Multimodal Language Models (MLMs) have demonstrated exceptional general language and imagery tasking performance. Therefore, it is interesting to unlock MLM's potential to be 3D generalist for wider tasks. However, current MLMs' research has been less focused on 3D tasks due to a lack of large-scale 3D instruction-following datasets. In this work, we introduce a comprehensive 3D instructionfollowing dataset called M3DBench, which possesses the following characteristics: 1) It supports general multimodal instructions interleaved with text, images, 3D objects, and other visual prompts. 2) It unifies diverse 3D tasks at both region and scene levels, covering a variety of fundamental abilities in real-world 3D environments. 3) It is a large-scale 3D instruction-following dataset with over 320k instruction-response pairs. Furthermore, we establish a new benchmark for assessing the performance of large models in understanding multi-modal 3D prompts. Extensive experiments demonstrate the effectiveness of our dataset and baseline, supporting general 3D-centric tasks, which can inspire future research.

cs.CV↗

arXiv2023

LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning

Recent advances in Large Multimodal Models (LMM) have made it possible for various applications in human-machine interactions. However, developing LMMs that can comprehend, reason, and plan in complex and diverse 3D environments remains a challenging topic, especially considering the demand for understanding permutation-invariant point cloud 3D representations of the 3D scene. Existing works seek help from multi-view images, and project 2D features to 3D space as 3D scene representations. This, however, leads to huge computational overhead and performance degradation. In this paper, we present LL3DA, a Large Language 3D Assistant that takes point cloud as direct input and respond to both textual-instructions and visual-prompts. This help LMMs better comprehend human interactions and further help to remove the ambiguities in cluttered 3D scenes. Experiments show that LL3DA achieves remarkable results, and surpasses various 3D vision-language models on both 3D Dense Captioning and 3D Question Answering.

cs.CV↗

arXiv2023

Exploiting Semantic Role Contextualized Video Features for Multi-Instance Text-Video Retrieval EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2022

In this report, we present our approach for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2022. We first parse sentences into semantic roles corresponding to verbs and nouns; then utilize self-attentions to exploit semantic role contextualized video features along with textual features via triplet losses in multiple embedding spaces. Our method overpasses the strong baseline in normalized Discounted Cumulative Gain (nDCG), which is more valuable for semantic similarity. Our submission is ranked 3rd for nDCG and ranked 4th for mAP.

cs.CV↗

arXiv2023

Towards Debiasing Frame Length Bias in Text-Video Retrieval via Causal Intervention

Many studies focus on improving pretraining or developing new backbones in text-video retrieval. However, existing methods may suffer from the learning and inference bias issue, as recent research suggests in other text-video-related tasks. For instance, spatial appearance features on action recognition or temporal object co-occurrences on video scene graph generation could induce spurious correlations. In this work, we present a unique and systematic study of a temporal bias due to frame length discrepancy between training and test sets of trimmed video clips, which is the first such attempt for a text-video retrieval task, to the best of our knowledge. We first hypothesise and verify the bias on how it would affect the model illustrated with a baseline study. Then, we propose a causal debiasing approach and perform extensive experiments and ablation studies on the Epic-Kitchens-100, YouCook2, and MSR-VTT datasets. Our model overpasses the baseline and SOTA on nDCG, a semantic-relevancy-focused evaluation metric which proves the bias is mitigated, as well as on the other conventional metrics.

cs.CV↗

arXiv2023

Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning

3D dense captioning requires a model to translate its understanding of an input 3D scene into several captions associated with different object regions. Existing methods adopt a sophisticated "detect-then-describe" pipeline, which builds explicit relation modules upon a 3D detector with numerous hand-crafted components. While these methods have achieved initial success, the cascade pipeline tends to accumulate errors because of duplicated and inaccurate box estimations and messy 3D scenes. In this paper, we first propose Vote2Cap-DETR, a simple-yet-effective transformer framework that decouples the decoding process of caption generation and object localization through parallel decoding. Moreover, we argue that object localization and description generation require different levels of scene understanding, which could be challenging for a shared set of queries to capture. To this end, we propose an advanced version, Vote2Cap-DETR++, which decouples the queries into localization and caption queries to capture task-specific features. Additionally, we introduce the iterative spatial refinement strategy to vote queries for faster convergence and better localization performance. We also insert additional spatial information to the caption head for more accurate descriptions. Without bells and whistles, extensive experiments on two commonly used datasets, ScanRefer and Nr3D, demonstrate Vote2Cap-DETR and Vote2Cap-DETR++ surpass conventional "detect-then-describe" methods by a large margin. Codes will be made available at https://github.com/ch3cook-fdu/Vote2Cap-DETR.

cs.CV↗

arXiv2023

Multi-view Vision-Prompt Fusion Network: Can 2D Pre-trained Model Boost 3D Point Cloud Data-scarce Learning?

Point cloud based 3D deep model has wide applications in many applications such as autonomous driving, house robot, and so on. Inspired by the recent prompt learning in natural language processing, this work proposes a novel Multi-view Vision-Prompt Fusion Network (MvNet) for few-shot 3D point cloud classification. MvNet investigates the possibility of leveraging the off-the-shelf 2D pre-trained models to achieve the few-shot classification, which can alleviate the over-dependence issue of the existing baseline models towards the large-scale annotated 3D point cloud data. Specifically, MvNet first encodes a 3D point cloud into multi-view image features for a number of different views. Then, a novel multi-view prompt fusion module is developed to effectively fuse information from different views to bridge the gap between 3D point cloud data and 2D pre-trained models. A set of 2D image prompts can then be derived to better describe the suitable prior knowledge for a large-scale pre-trained image model for few-shot 3D point cloud classification. Extensive experiments on ModelNet, ScanObjectNN, and ShapeNet datasets demonstrate that MvNet achieves new state-of-the-art performance for 3D few-shot point cloud image classification. The source code of this work will be available soon.

cs.CV↗

arXiv2023

Self-Supervised Learning for WiFi CSI-Based Human Activity Recognition: A Systematic Study

Recently, with the advancement of the Internet of Things (IoT), WiFi CSI-based HAR has gained increasing attention from academic and industry communities. By integrating the deep learning technology with CSI-based HAR, researchers achieve state-of-the-art performance without the need of expert knowledge. However, the scarcity of labeled CSI data remains the most prominent challenge when applying deep learning models in the context of CSI-based HAR due to the privacy and incomprehensibility of CSI-based HAR data. On the other hand, SSL has emerged as a promising approach for learning meaningful representations from data without heavy reliance on labeled examples. Therefore, considerable efforts have been made to address the challenge of insufficient data in deep learning by leveraging SSL algorithms. In this paper, we undertake a comprehensive inventory and analysis of the potential held by different categories of SSL algorithms, including those that have been previously studied and those that have not yet been explored, within the field. We provide an in-depth investigation of SSL algorithms in the context of WiFi CSI-based HAR. We evaluate four categories of SSL algorithms using three publicly available CSI HAR datasets, each encompassing different tasks and environmental settings. To ensure relevance to real-world applications, we design performance metrics that align with specific requirements. Furthermore, our experimental findings uncover several limitations and blind spots in existing work, highlighting the barriers that need to be addressed before SSL can be effectively deployed in real-world WiFi-based HAR applications. Our results also serve as a practical guideline for industry practitioners and provide valuable insights for future research endeavors in this field.

eess.SP↗

arXiv2023

An Overview of Challenges in Egocentric Text-Video Retrieval

Text-video retrieval contains various challenges, including biases coming from diverse sources. We highlight some of them supported by illustrations to open a discussion. Besides, we address one of the biases, frame length bias, with a simple method which brings a very incremental but promising increase. We conclude with future directions.

cs.CV↗

arXiv2023

Scene Text Synthesis for Efficient and Effective Deep Network Training

A large amount of annotated training images is critical for training accurate and robust deep network models but the collection of a large amount of annotated training images is often time-consuming and costly. Image synthesis alleviates this constraint by generating annotated training images automatically by machines which has attracted increasing interest in the recent deep learning research. We develop an innovative image synthesis technique that composes annotated training images by realistically embedding foreground objects of interest (OOI) into background images. The proposed technique consists of two key components that in principle boost the usefulness of the synthesized images in deep network training. The first is context-aware semantic coherence which ensures that the OOI are placed around semantically coherent regions within the background image. The second is harmonious appearance adaptation which ensures that the embedded OOI are agreeable to the surrounding background from both geometry alignment and appearance realism. The proposed technique has been evaluated over two related but very different computer vision challenges, namely, scene text detection and scene text recognition. Experiments over a number of public datasets demonstrate the effectiveness of our proposed image synthesis technique - the use of our synthesized images in deep network training is capable of achieving similar or even better scene text detection and scene text recognition performance as compared with using real images.

cs.CV↗

arXiv2023

What Makes for Effective Few-shot Point Cloud Classification?

Due to the emergence of powerful computing resources and large-scale annotated datasets, deep learning has seen wide applications in our daily life. However, most current methods require extensive data collection and retraining when dealing with novel classes never seen before. On the other hand, we humans can quickly recognize new classes by looking at a few samples, which motivates the recent popularity of few-shot learning (FSL) in machine learning communities. Most current FSL approaches work on 2D image domain, however, its implication in 3D perception is relatively under-explored. Not only needs to recognize the unseen examples as in 2D domain, 3D few-shot learning is more challenging with unordered structures, high intra-class variances, and subtle inter-class differences. Moreover, different architectures and learning algorithms make it difficult to study the effectiveness of existing 2D methods when migrating to the 3D domain. In this work, for the first time, we perform systematic and extensive studies of recent 2D FSL and 3D backbone networks for benchmarking few-shot point cloud classification, and we suggest a strong baseline and learning architectures for 3D FSL. Then, we propose a novel plug-and-play component called Cross-Instance Adaptation (CIA) module, to address the high intra-class variances and subtle inter-class differences issues, which can be easily inserted into current baselines with significant performance improvement. Extensive experiments on two newly introduced benchmark datasets, ModelNet40-FS and ShapeNet70-FS, demonstrate the superiority of our proposed network for 3D FSL.

cs.CV↗

arXiv2023

A Closer Look at Few-Shot 3D Point Cloud Classification

In recent years, research on few-shot learning (FSL) has been fast-growing in the 2D image domain due to the less requirement for labeled training data and greater generalization for novel classes. However, its application in 3D point cloud data is relatively under-explored. Not only need to distinguish unseen classes as in the 2D domain, 3D FSL is more challenging in terms of irregular structures, subtle inter-class differences, and high intra-class variances {when trained on a low number of data.} Moreover, different architectures and learning algorithms make it difficult to study the effectiveness of existing 2D FSL algorithms when migrating to the 3D domain. In this work, for the first time, we perform systematic and extensive investigations of directly applying recent 2D FSL works to 3D point cloud related backbone networks and thus suggest a strong learning baseline for few-shot 3D point cloud classification. Furthermore, we propose a new network, Point-cloud Correlation Interaction (PCIA), with three novel plug-and-play components called Salient-Part Fusion (SPF) module, Self-Channel Interaction Plus (SCI+) module, and Cross-Instance Fusion Plus (CIF+) module to obtain more representative embeddings and improve the feature distinction. These modules can be inserted into most FSL algorithms with minor changes and significantly improve the performance. Experimental results on three benchmark datasets, ModelNet40-FS, ShapeNet70-FS, and ScanObjectNN-FS, demonstrate that our method achieves state-of-the-art performance for the 3D FSL task. Code and datasets are available at https://github.com/cgye96/A_Closer_Look_At_3DFSL.

cs.CV↗

arXiv2023

End-to-End 3D Dense Captioning with Vote2Cap-DETR

3D dense captioning aims to generate multiple captions localized with their associated object regions. Existing methods follow a sophisticated ``detect-then-describe'' pipeline equipped with numerous hand-crafted components. However, these hand-crafted components would yield suboptimal performance given cluttered object spatial and class distributions among different scenes. In this paper, we propose a simple-yet-effective transformer framework Vote2Cap-DETR based on recent popular \textbf{DE}tection \textbf{TR}ansformer (DETR). Compared with prior arts, our framework has several appealing advantages: 1) Without resorting to numerous hand-crafted components, our method is based on a full transformer encoder-decoder architecture with a learnable vote query driven object decoder, and a caption decoder that produces the dense captions in a set-prediction manner. 2) In contrast to the two-stage scheme, our method can perform detection and captioning in one-stage. 3) Without bells and whistles, extensive experiments on two commonly used datasets, ScanRefer and Nr3D, demonstrate that our Vote2Cap-DETR surpasses current state-of-the-arts by 11.13\% and 7.11\% in CIDEr@0.5IoU, respectively. Codes will be released soon.

cs.CV↗

arXiv2022

Point Cloud Instance Segmentation with Semi-supervised Bounding-Box Mining

Point cloud instance segmentation has achieved huge progress with the emergence of deep learning. However, these methods are usually data-hungry with expensive and time-consuming dense point cloud annotations. To alleviate the annotation cost, unlabeled or weakly labeled data is still less explored in the task. In this paper, we introduce the first semi-supervised point cloud instance segmentation framework (SPIB) using both labeled and unlabelled bounding boxes as supervision. To be specific, our SPIB architecture involves a two-stage learning procedure. For stage one, a bounding box proposal generation network is trained under a semi-supervised setting with perturbation consistency regularization (SPCR). The regularization works by enforcing an invariance of the bounding box predictions over different perturbations applied to the input point clouds, to provide self-supervision for network learning. For stage two, the bounding box proposals with SPCR are grouped into some subsets, and the instance masks are mined inside each subset with a novel semantic propagation module and a property consistency graph module. Moreover, we introduce a novel occupancy ratio guided refinement module to refine the instance masks. Extensive experiments on the challenging ScanNet v2 dataset demonstrate our method can achieve competitive performance compared with the recent fully-supervised methods.

cs.CV↗

arXiv2022

RoME: Role-aware Mixture-of-Expert Transformer for Text-to-Video Retrieval

Seas of videos are uploaded daily with the popularity of social channels; thus, retrieving the most related video contents with user textual queries plays a more crucial role. Most methods consider only one joint embedding space between global visual and textual features without considering the local structures of each modality. Some other approaches consider multiple embedding spaces consisting of global and local features separately, ignoring rich inter-modality correlations. We propose a novel mixture-of-expert transformer RoME that disentangles the text and the video into three levels; the roles of spatial contexts, temporal contexts, and object contexts. We utilize a transformer-based attention mechanism to fully exploit visual and text embeddings at both global and local levels with mixture-of-experts for considering inter-modalities and structures' correlations. The results indicate that our method outperforms the state-of-the-art methods on the YouCook2 and MSR-VTT datasets, given the same visual backbone without pre-training. Finally, we conducted extensive ablation studies to elucidate our design choices.

cs.CV↗