Zixu Zhao

Yueming Jin, Yang Yu, Cheng Chen et al.

Automatic surgical scene segmentation is fundamental for facilitating cognitive intelligence in the modern operating theatre. Previous works rely on conventional aggregation modules (e.g., dilated convolution, convolutional LSTM), which only make use of the local context. In this paper, we propose a novel framework STswinCL that explores the complementary intra- and inter-video relations to boost segmentation performance, by progressively capturing the global context. We firstly develop a hierarchy Transformer to capture intra-video relation that includes richer spatial and temporal cues from neighbor pixels and previous frames. A joint space-time window shift scheme is proposed to efficiently aggregate these two cues into each pixel embedding. Then, we explore inter-video relation via pixel-to-pixel contrastive learning, which well structures the global embedding space. A multi-source contrast training objective is developed to group the pixel embeddings across videos with the ground-truth guidance, which is crucial for learning the global property of the whole data. We extensively validate our approach on two public surgical video benchmarks, including EndoVis18 Challenge and CaDIS dataset. Experimental results demonstrate the promising performance of our method, which consistently exceeds previous state-of-the-art approaches. Code is available at https://github.com/YuemingJin/STswinCL.

Pengfei Li, Gang Liu, Jinlong He et al.

Medical visual question answering (VQA) is a challenging task that requires answering clinical questions of a given medical image, by taking consider of both visual and language information. However, due to the small scale of training data for medical VQA, pre-training fine-tuning paradigms have been a commonly used solution to improve model generalization performance. In this paper, we present a novel self-supervised approach that learns unimodal and multimodal feature representations of input images and text using medical image caption datasets, by leveraging both unimodal and multimodal contrastive losses, along with masked language modeling and image text matching as pretraining objectives. The pre-trained model is then transferred to downstream medical VQA tasks. The proposed approach achieves state-of-the-art (SOTA) performance on three publicly available medical VQA datasets with significant accuracy improvements of 2.2%, 14.7%, and 1.7% respectively. Besides, we conduct a comprehensive analysis to validate the effectiveness of different components of the approach and study different pre-training settings. Our codes and models are available at https://github.com/pengfeiliHEU/MUMC.

Ke Fan, Zechen Bai, Tianjun Xiao et al. · eth-zurich

In this paper, we show that recent advances in video representation learning and pre-trained vision-language models allow for substantial improvements in self-supervised video object localization. We propose a method that first localizes objects in videos via an object-centric approach with slot attention and then assigns text to the obtained slots. The latter is achieved by an unsupervised way to read localized semantic information from the pre-trained CLIP model. The resulting video object localization is entirely unsupervised apart from the implicit annotation contained in CLIP, and it is effectively the first unsupervised approach that yields good results on regular video benchmarks.

Yi Wang, Jiaze Wang, Jinpeng Li et al.

Data augmentation is an effective regularization strategy for mitigating overfitting in deep neural networks, and it plays a crucial role in 3D vision tasks, where the point cloud data is relatively limited. While mixing-based augmentation has shown promise for point clouds, previous methods mix point clouds either on block level or point level, which has constrained their ability to strike a balance between generating diverse training samples and preserving the local characteristics of point clouds. Additionally, the varying importance of each part of the point clouds has not been fully considered, cause not all parts contribute equally to the classification task, and some parts may contain unimportant or redundant information. To overcome these challenges, we propose PointPatchMix, a novel approach that mixes point clouds at the patch level and integrates a patch scoring module to generate content-based targets for mixed point clouds. Our approach preserves local features at the patch level, while the patch scoring module assigns targets based on the content-based significance score from a pre-trained teacher model. We evaluate PointPatchMix on two benchmark datasets, ModelNet40 and ScanObjectNN, and demonstrate significant improvements over various baselines in both synthetic and real-world datasets, as well as few-shot settings. With Point-MAE as our baseline, our model surpasses previous methods by a significant margin, achieving 86.3% accuracy on ScanObjectNN and 94.1% accuracy on ModelNet40. Furthermore, our approach shows strong generalization across multiple architectures and enhances the robustness of the baseline model.

Yang Yu, Zixu Zhao, Yueming Jin et al.

Surgical scene segmentation is fundamentally crucial for prompting cognitive assistance in robotic surgery. However, pixel-wise annotating surgical video in a frame-by-frame manner is expensive and time consuming. To greatly reduce the labeling burden, in this work, we study semi-supervised scene segmentation from robotic surgical video, which is practically essential yet rarely explored before. We consider a clinically suitable annotation situation under the equidistant sampling. We then propose PGV-CL, a novel pseudo-label guided cross-video contrast learning method to boost scene segmentation. It effectively leverages unlabeled data for a trusty and global model regularization that produces more discriminative feature representation. Concretely, for trusty representation learning, we propose to incorporate pseudo labels to instruct the pair selection, obtaining more reliable representation pairs for pixel contrast. Moreover, we expand the representation learning space from previous image-level to cross-video, which can capture the global semantics to benefit the learning process. We extensively evaluate our method on a public robotic surgery dataset EndoVis18 and a public cataract dataset CaDIS. Experimental results demonstrate the effectiveness of our method, consistently outperforming the state-of-the-art semi-supervised methods under different labeling ratios, and even surpassing fully supervised training on EndoVis18 with 10.1% labeling.

Jiaxin Cheng, Zixu Zhao, Tong He et al.

Recent advancements in generative models have significantly enhanced their capacity for image generation, enabling a wide range of applications such as image editing, completion and video editing. A specialized area within generative modeling is layout-to-image (L2I) generation, where predefined layouts of objects guide the generative process. In this study, we introduce a novel regional cross-attention module tailored to enrich layout-to-image generation. This module notably improves the representation of layout regions, particularly in scenarios where existing methods struggle with highly complex and detailed textual descriptions. Moreover, while current open-vocabulary L2I methods are trained in an open-set setting, their evaluations often occur in closed-set environments. To bridge this gap, we propose two metrics to assess L2I performance in open-vocabulary scenarios. Additionally, we conduct a comprehensive user study to validate the consistency of these metrics with human preferences.

Zixu Zhao, Sijin Wang, Yu Hou et al.

Tourism is a high-stakes setting for conversational recommender systems (CRS): a plausible-sounding suggestion can waste real money and trip time once a traveler acts on it. Existing CRS benchmarks primarily evaluate systems with a single Recall@k score over entity mentions, and tourism-specific resources add spatial or knowledge-graph context, yet none of them couple multi-turn recommendation with verbatim review-span evidence and rejection recovery. This leaves an evaluation gap for tourism recommendation that is simultaneously trustworthy, verifiable, and adaptive: recommend the right point of interest (POI) for multi-aspect preferences (such as cuisine, price, atmosphere, walking distance), justify each suggestion with verifiable evidence from prior visitors so the traveler can act without trial and error, and recover when the first recommendation is rejected mid-dialogue. We introduce TRACE, where each item is a multi-turn tourism recommendation dialogue with review-span citations and explicit rejection turns: 10,000 dialogues over 2,400 Yelp POIs and 34,208 reviews across eight U.S. cities, paired with 14 retrieval, planning, and LLM baselines, along with 25 metrics organized under Accuracy, Grounding, and Recovery. Across these baselines, TRACE reveals the Three-Competency Gap: LLM Zero-Shot leads in closed-set Recall@1 and rejection recovery but cites less densely than retrievers; non-LLM retrievers achieve surface-verbatim grounding but with low accuracy; Multi-Review Synthesis fails at recovery. The Grounding Score agrees with human citation precision (Spearman rho=+0.80, p<10^-20), and paired t-tests reproduce the per-baseline ranking (p<0.01 on the dominant contrasts). TRACE reframes accountable tourism recommendation as a joint target (right POI, verifiable evidence, adaptive repair) rather than a single-axis leaderboard.

Pinxue Guo, Zixu Zhao, Jianxiong Gao et al.

Video segmentation is essential for advancing robotics and autonomous driving, particularly in open-world settings where continuous perception and object association across video frames are critical. While the Segment Anything Model (SAM) has excelled in static image segmentation, extending its capabilities to video segmentation poses significant challenges. We tackle two major hurdles: a) SAM's embedding limitations in associating objects across frames, and b) granularity inconsistencies in object segmentation. To this end, we introduce VideoSAM, an end-to-end framework designed to address these challenges by improving object tracking and segmentation consistency in dynamic environments. VideoSAM integrates an agglomerated backbone, RADIO, enabling object association through similarity metrics and introduces Cycle-ack-Pairs Propagation with a memory mechanism for stable object tracking. Additionally, we incorporate an autoregressive object-token mechanism within the SAM decoder to maintain consistent granularity across frames. Our method is extensively evaluated on the UVO and BURST benchmarks, and robotic videos from RoboTAP, demonstrating its effectiveness and robustness in real-world scenarios. All codes will be available.

Zixu Zhao, Yang Zhan

Unmanned aerial vehicles (UAVs) have become powerful platforms for real-time, high-resolution data collection, producing massive volumes of aerial videos. Efficient retrieval of relevant content from these videos is crucial for applications in urban management, emergency response, security, and disaster relief. While text-video retrieval has advanced in natural video domains, the UAV domain remains underexplored due to limitations in existing datasets, such as coarse and redundant captions. Thus, in this work, we construct the Drone Video-Text Match Dataset (DVTMD), which contains 2,864 videos and 14,320 fine-grained, semantically diverse captions. The annotations capture multiple complementary aspects, including human actions, objects, background settings, environmental conditions, and visual style, thereby enhancing text-video correspondence and reducing redundancy. Building on this dataset, we propose the Text-Conditioned Multi-granularity Alignment (TCMA) framework, which integrates global video-sentence alignment, sentence-guided frame aggregation, and word-guided patch alignment. To further refine local alignment, we design a Word and Patch Selection module that filters irrelevant content, as well as a Text-Adaptive Dynamic Temperature Mechanism that adapts attention sharpness to text type. Extensive experiments on DVTMD and CapERA establish the first complete benchmark for drone text-video retrieval. Our TCMA achieves state-of-the-art performance, including 45.5% R@1 in text-to-video and 42.8% R@1 in video-to-text retrieval, demonstrating the effectiveness of our dataset and method. The code and dataset will be released.

Zixu Zhao, Jiaze Wang, Max Horn et al.

Unsupervised object-centric learning methods allow the partitioning of scenes into entities without additional localization information and are excellent candidates for reducing the annotation burden of multiple-object tracking (MOT) pipelines. Unfortunately, they lack two key properties: objects are often split into parts and are not consistently tracked over time. In fact, state-of-the-art models achieve pixel-level accuracy and temporal consistency by relying on supervised object detection with additional ID labels for the association through time. This paper proposes a video object-centric model for MOT. It consists of an index-merge module that adapts the object-centric slots into detection outputs and an object memory module that builds complete object prototypes to handle occlusions. Benefited from object-centric learning, we only require sparse detection labels (0%-6.25%) for object localization and feature binding. Relying on our self-supervised Expectation-Maximization-inspired loss for object association, our approach requires no ID labels. Our experiments significantly narrow the gap between the existing object-centric model and the fully supervised state-of-the-art and outperform several unsupervised trackers.

Zixu Zhao, Yueming Jin, Pheng-Ann Heng

Surgical instrument segmentation -- in general a pixel classification task -- is fundamentally crucial for promoting cognitive intelligence in robot-assisted surgery (RAS). However, previous methods are struggling with discriminating instrument types and instances. To address the above issues, we explore a mask classification paradigm that produces per-segment predictions. We propose TraSeTR, a novel Track-to-Segment Transformer that wisely exploits tracking cues to assist surgical instrument segmentation. TraSeTR jointly reasons about the instrument type, location, and identity with instance-level predictions i.e., a set of class-bbox-mask pairs, by decoding query embeddings. Specifically, we introduce the prior query that encoded with previous temporal knowledge, to transfer tracking signals to current instances via identity matching. A contrastive query learning strategy is further applied to reshape the query feature space, which greatly alleviates the tracking difficulty caused by large temporal variations. The effectiveness of our method is demonstrated with state-of-the-art instrument type segmentation results on three public datasets, including two RAS benchmarks from EndoVis Challenges and one cataract surgery dataset CaDIS.

Zixu Zhao, Yueming Jin, Pheng-Ann Heng

This paper presents a self-supervised method for learning reliable visual correspondence from unlabeled videos. We formulate the correspondence as finding paths in a joint space-time graph, where nodes are grid patches sampled from frames, and are linked by two types of edges: (i) neighbor relations that determine the aggregation strength from intra-frame neighbors in space, and (ii) similarity relations that indicate the transition probability of inter-frame paths across time. Leveraging the cycle-consistency in videos, our contrastive learning objective discriminates dynamic objects from both their neighboring views and temporal views. Compared with prior works, our approach actively explores the neighbor relations of central instances to learn a latent association between center-neighbor pairs (e.g., "hand -- arm") across time, thus improving the instance discrimination. Without fine-tuning, our learned representation outperforms the state-of-the-art self-supervised methods on a variety of visual tasks including video object propagation, part propagation, and pose keypoint tracking. Our self-supervised method also surpasses some fully supervised algorithms designed for the specific tasks.

Yueming Jin, Yonghao Long, Cheng Chen et al.

Automatic surgical workflow recognition is a key component for developing context-aware computer-assisted systems in the operating theatre. Previous works either jointly modeled the spatial features with short fixed-range temporal information, or separately learned visual and long temporal cues. In this paper, we propose a novel end-to-end temporal memory relation network (TMRNet) for relating long-range and multi-scale temporal patterns to augment the present features. We establish a long-range memory bank to serve as a memory cell storing the rich supportive information. Through our designed temporal variation layer, the supportive cues are further enhanced by multi-scale temporal-only convolutions. To effectively incorporate the two types of cues without disturbing the joint learning of spatio-temporal features, we introduce a non-local bank operator to attentively relate the past to the present. In this regard, our TMRNet enables the current feature to view the long-range temporal dependency, as well as tolerate complex temporal extents. We have extensively validated our approach on two benchmark surgical video datasets, M2CAI challenge dataset and Cholec80 dataset. Experimental results demonstrate the outstanding performance of our method, consistently exceeding the state-of-the-art methods by a large margin (e.g., 67.0% v.s. 78.9% Jaccard on Cholec80 dataset).

Zixu Zhao, Yueming Jin, Bo Lu et al.

Surgical instrument segmentation in robot-assisted surgery (RAS) - especially that using learning-based models - relies on the assumption that training and testing videos are sampled from the same domain. However, it is impractical and expensive to collect and annotate sufficient data from every new domain. To greatly increase the label efficiency, we explore a new problem, i.e., adaptive instrument segmentation, which is to effectively adapt one source model to new robotic surgical videos from multiple target domains, only given the annotated instruments in the first frame. We propose MDAL, a meta-learning based dynamic online adaptive learning scheme with a two-stage framework to fast adapt the model parameters on the first frame and partial subsequent frames while predicting the results. MDAL learns the general knowledge of instruments and the fast adaptation ability through the video-specific meta-learning paradigm. The added gradient gate excludes the noisy supervision from pseudo masks for dynamic online adaptation on target videos. We demonstrate empirically that MDAL outperforms other state-of-the-art methods on two datasets (including a real-world RAS dataset). The promising performance on ex-vivo scenes also benefits the downstream tasks such as robot-assisted suturing and camera control.

Xiaojie Gao, Yueming Jin, Zixu Zhao et al.

Predicting future frames for robotic surgical video is an interesting, important yet extremely challenging problem, given that the operative tasks may have complex dynamics. Existing approaches on future prediction of natural videos were based on either deterministic models or stochastic models, including deep recurrent neural networks, optical flow, and latent space modeling. However, the potential in predicting meaningful movements of robots with dual arms in surgical scenarios has not been tapped so far, which is typically more challenging than forecasting independent motions of one arm robots in natural scenarios. In this paper, we propose a ternary prior guided variational autoencoder (TPG-VAE) model for future frame prediction in robotic surgical video sequences. Besides content distribution, our model learns motion distribution, which is novel to handle the small movements of surgical tools. Furthermore, we add the invariant prior information from the gesture class into the generation process to constrain the latent space of our model. To our best knowledge, this is the first time that the future frames of dual arm robots are predicted considering their unique characteristics relative to general robotic videos. Experiments demonstrate that our model gains more stable and realistic future frame prediction scenes with the suturing task on the public JIGSAWS dataset.

Zixu Zhao, Yueming Jin, Xiaojie Gao et al.

Performing low hertz labeling for surgical videos at intervals can greatly releases the burden of surgeons. In this paper, we study the semi-supervised instrument segmentation from robotic surgical videos with sparse annotations. Unlike most previous methods using unlabeled frames individually, we propose a dual motion based method to wisely learn motion flows for segmentation enhancement by leveraging temporal dynamics. We firstly design a flow predictor to derive the motion for jointly propagating the frame-label pairs given the current labeled frame. Considering the fast instrument motion, we further introduce a flow compensator to estimate intermediate motion within continuous frames, with a novel cycle learning strategy. By exploiting generated data pairs, our framework can recover and even enhance temporal consistency of training sequences to benefit segmentation. We validate our framework with binary, part, and type tasks on 2017 MICCAI EndoVis Robotic Instrument Segmentation Challenge dataset. Results show that our method outperforms the state-of-the-art semi-supervised methods by a large margin, and even exceeds fully supervised training on two tasks.

Zixu Zhao, Huangjing Lin, Hao Chen et al.

Automatic detection of cancer metastasis from whole slide images (WSIs) is a crucial step for following patient staging and prognosis. Recent convolutional neural network based approaches are struggling with the trade-off between accuracy and computational efficiency due to the difficulty in processing large-scale gigapixel WSIs. To meet this challenge, we propose a novel Pyramidal Feature Aggregation ScanNet (PFA-ScanNet) for robust and fast analysis of breast cancer metastasis. Our method mainly benefits from the aggregation of extracted local-to-global features with diverse receptive fields, as well as the proposed synergistic learning for training the main detector and extra decoder with semantic guidance. Furthermore, a high-efficiency inference mechanism is designed with dense pooling layers, which allows dense and fast scanning for gigapixel WSI analysis. As a result, the proposed PFA-ScanNet achieved the state-of-the-art FROC of 90.2% on the Camelyon16 dataset, as well as competitive kappa score of 0.905 on the Camelyon17 leaderboard. In addition, our method shows leading speed advantage over other methods, about 7.2 min per WSI with a single GPU, making automatic analysis of breast cancer metastasis more applicable in the clinical usage.

Zixu Zhao

America has a massive railway system. As of 2006, U.S. freight railroads have 140,490 route- miles of standard gauge, but maintaining such a huge system and eliminating any dangers, like reduced track stability and poor drainage, caused by railway ballast degradation require huge amount of labor. The traditional way to quantify the degradation of ballast is to use an index called Fouling Index (FI) through ballast sampling and sieve analysis. However, determining the FI values in lab is very time-consuming and laborious, but with the help of recent development in the field of computer vision, a novel method for a potential machine-vison based ballast inspection system can be employed that can hopefully replace the traditional mechanical method. The new machine-vision approach analyses the images of the in-service ballasts, and then utilizes image segmentation algorithm to get ballast segments. By comparing the segment results and their corresponding FI values, this novel method produces a machine-vision-based index that has the best-fit relation with FI. The implementation details of how this algorithm works are discussed in this report.

Fouad Amer, Zixu Zhao, Siwei Tang et al.

This paper aims at finding a method to register two different point clouds constructed by ORB-SLAM2 and OpenSfM. To do this, we post some tags with unique textures in the scene and take videos and photos of that area. Then we take short videos of only the tags to extract their features. By matching the ORB feature of the tags with their corresponding features in the scene, it is then possible to localize the position of these tags both in point clouds constructed by ORB-SLAM2 and OpenSfM. Thus, the best transformation matrix between two point clouds can be calculated, and the two point clouds can be aligned.

Qianye Yang, Nannan Li, Zixu Zhao et al.

We present a cross-modality generation framework that learns to generate translated modalities from given modalities in MR images without real acquisition. Our proposed method performs NeuroImage-to-NeuroImage translation (abbreviated as N2N) by means of a deep learning model that leverages conditional generative adversarial networks (cGANs). Our framework jointly exploits the low-level features (pixel-wise information) and high-level representations (e.g. brain tumors, brain structure like gray matter, etc.) between cross modalities which are important for resolving the challenging complexity in brain structures. Our framework can serve as an auxiliary method in clinical diagnosis and has great application potential. Based on our proposed framework, we first propose a method for cross-modality registration by fusing the deformation fields to adopt the cross-modality information from translated modalities. Second, we propose an approach for MRI segmentation, translated multichannel segmentation (TMS), where given modalities, along with translated modalities, are segmented by fully convolutional networks (FCN) in a multichannel manner. Both of these two methods successfully adopt the cross-modality information to improve the performance without adding any extra data. Experiments demonstrate that our proposed framework advances the state-of-the-art on five brain MRI datasets. We also observe encouraging results in cross-modality registration and segmentation on some widely adopted brain datasets. Overall, our work can serve as an auxiliary method in clinical diagnosis and be applied to various tasks in medical fields. Keywords: image-to-image, cross-modality, registration, segmentation, brain MRI