arXiv subjects

Xiaoqiang Zhang

Publications and source records attributed to Xiaoqiang Zhang.

9 recordsLinked to original sources

arXiv2026

LifelongCrossNav: Persistent 3D Semantic Memory for Cross-Floor Multi-Object Navigation

Object-goal navigation has made substantial progress in semantic perception and exploration, yet persistent memory for multi-object navigation and cross-floor navigation are still commonly addressed separately. We present LifelongCrossNav, a framework for sequential multi-object ObjectNav in unknown multi-floor indoor environments. Within each episode, the agent receives an ordered sequence of object-goal queries while continuously maintaining a shared sparse 3D semantic voxel memory. This memory incrementally accumulates geometric structure, traversability states, and vision-language features, allowing subsequent object-goal queries to retrieve previously acquired scene information without rebuilding the map. To support persistent search across floors, LifelongCrossNav combines support-aware 3D traversability mapping, stair-specific perception, and direction-aware stair traversal. A unified navigation policy coordinates same-floor frontier exploration, live and historical point-of-interest retrieval, stair navigation, and target-object search and approach. We further introduce HM3D-MFMON, a benchmark for sequential Multi-Floor Multi-Object Navigation built on HM3D scenes, including a dedicated subset in which completing the full sequence of object-goal subtasks requires at least one floor transition. Experimental results show that LifelongCrossNav consistently outperforms a representative planar persistent semantic-map baseline on HM3D-MFMON, demonstrating that persistent 3D semantic memory and cross-floor traversability modeling effectively support sequential multi-object navigation in multi-floor environments. Project page: https://flageval-baai.github.io/LifelongCrossNavPage.

cs.RO↗

arXiv2024

TextFormer: A Query-based End-to-End Text Spotter with Mixed Supervision

End-to-end text spotting is a vital computer vision task that aims to integrate scene text detection and recognition into a unified framework. Typical methods heavily rely on Region-of-Interest (RoI) operations to extract local features and complex post-processing steps to produce final predictions. To address these limitations, we propose TextFormer, a query-based end-to-end text spotter with Transformer architecture. Specifically, using query embedding per text instance, TextFormer builds upon an image encoder and a text decoder to learn a joint semantic understanding for multi-task modeling. It allows for mutual training and optimization of classification, segmentation, and recognition branches, resulting in deeper feature sharing without sacrificing flexibility or simplicity. Additionally, we design an Adaptive Global aGgregation (AGG) module to transfer global features into sequential features for reading arbitrarily-shaped texts, which overcomes the sub-optimization problem of RoI operations. Furthermore, potential corpus information is utilized from weak annotations to full labels through mixed supervision, further improving text detection and end-to-end text spotting results. Extensive experiments on various bilingual (i.e., English and Chinese) benchmarks demonstrate the superiority of our method. Especially on TDA-ReCTS dataset, TextFormer surpasses the state-of-the-art method in terms of 1-NED by 13.2%.

cs.CV↗

arXiv2024

Efficient Terahertz Generation from CoPt-based Terahertz Emitters via Orbital-to-Charge Conversion

Orbitronics devices operate by manipulating orbitally-polarized currents. Recent studies have shown that these orbital currents can be excited by femtosecond laser pulses in ferromagnet as Ni and converted into ultrafast charge current via orbital-to-charge conversion. However, the terahertz emission from orbitronic terahertz emitter based on Ni is still much weaker than the typical spintronic terahertz emitter. Here, we report more efficient light-induced generation of orbital current from CoPt alloy and the orbitronic terahertz emission by CoPt/Cu/MgO shows terahertz radiation comparable to that of efficient spintronic terahertz emitters. By varying the concentration of CoPt alloy, the thickness of Cu, and the capping layer, we confirm that THz emission primarily originates from the orbital accumulation generated within CoPt, propagating through Cu and followed by the subsequent orbital-to-charge conversion from the inverse orbital Rashba-Edelstein effect at the Cu/MgO interface. This study provides strong evidence for the very efficient orbital current generation in CoPt alloy, paving the way to efficient orbital terahertz emitters.

cond-mat.mes-hall↗

arXiv2023

StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training

In this paper, we present StrucTexTv2, an effective document image pre-training framework, by performing masked visual-textual prediction. It consists of two self-supervised pre-training tasks: masked image modeling and masked language modeling, based on text region-level image masking. The proposed method randomly masks some image regions according to the bounding box coordinates of text words. The objectives of our pre-training tasks are reconstructing the pixels of masked image regions and the corresponding masked tokens simultaneously. Hence the pre-trained encoder can capture more textual semantics in comparison to the masked image modeling that usually predicts the masked image patches. Compared to the masked multi-modal modeling methods for document image understanding that rely on both the image and text modalities, StrucTexTv2 models image-only input and potentially deals with more application scenarios free from OCR pre-processing. Extensive experiments on mainstream benchmarks of document image understanding demonstrate the effectiveness of StrucTexTv2. It achieves competitive or even new state-of-the-art performance in various downstream tasks such as image classification, layout analysis, table structure recognition, document OCR, and information extraction under the end-to-end scenario.

cs.CV↗

arXiv2021

Multi-Modal Sarcasm Detection Based on Contrastive Attention Mechanism

In the past decade, sarcasm detection has been intensively conducted in a textual scenario. With the popularization of video communication, the analysis in multi-modal scenarios has received much attention in recent years. Therefore, multi-modal sarcasm detection, which aims at detecting sarcasm in video conversations, becomes increasingly hot in both the natural language processing community and the multi-modal analysis community. In this paper, considering that sarcasm is often conveyed through incongruity between modalities (e.g., text expressing a compliment while acoustic tone indicating a grumble), we construct a Contras-tive-Attention-based Sarcasm Detection (ConAttSD) model, which uses an inter-modality contrastive attention mechanism to extract several contrastive features for an utterance. A contrastive feature represents the incongruity of information between two modalities. Our experiments on MUStARD, a benchmark multi-modal sarcasm dataset, demonstrate the effectiveness of the proposed ConAttSD model.

cs.CL↗

arXiv2021

PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network

The reading of arbitrarily-shaped text has received increasing research attention. However, existing text spotters are mostly built on two-stage frameworks or character-based methods, which suffer from either Non-Maximum Suppression (NMS), Region-of-Interest (RoI) operations, or character-level annotations. In this paper, to address the above problems, we propose a novel fully convolutional Point Gathering Network (PGNet) for reading arbitrarily-shaped text in real-time. The PGNet is a single-shot text spotter, where the pixel-level character classification map is learned with proposed PG-CTC loss avoiding the usage of character-level annotations. With a PG-CTC decoder, we gather high-level character classification vectors from two-dimensional space and decode them into text symbols without NMS and RoI operations involved, which guarantees high efficiency. Additionally, reasoning the relations between each character and its neighbors, a graph refinement module (GRM) is proposed to optimize the coarse recognition and improve the end-to-end performance. Experiments prove that the proposed method achieves competitive accuracy, meanwhile significantly improving the running speed. In particular, in Total-Text, it runs at 46.7 FPS, surpassing the previous spotters with a large margin.

cs.CV↗

arXiv2019

Magnetization reversal more rapidly by using an ultrashort square-wave laser pulse

With the feature of low-power magnetization manipulation at an ultrashort time scale, all optical switching (AOS) has been propelled to the forefront in investigations. To further speed up the magnetization reversal by manipulating ultrashort optical pulses, in this paper, one single square-wave laser pulse (SWLP) vie the combination of heating and Inverse Faraday Effect (IFE) is explored to excite the reversal of magnetization in a Co/Pt system. Simulation results show that the switching time of magnetization is 3 times faster than the using of a traditional Gaussian wave laser pulse (GWLP) under the same laser energy and pulse duration, and the threshold of AOS for the ferromagnet is 0.67 mJ/cm2. We furthermore demonstrate that the "heat accumulating effect" of laser-pulse is an important factor that influences the switching time, and a SWLP has a larger effect of heat accumulating than a GWLP.

cond-mat.mes-hall↗

arXiv2018

Hyperspectral Image Dataset for Benchmarking on Salient Object Detection

Many works have been done on salient object detection using supervised or unsupervised approaches on colour images. Recently, a few studies demonstrated that efficient salient object detection can also be implemented by using spectral features in visible spectrum of hyperspectral images from natural scenes. However, these models on hyperspectral salient object detection were tested with a very few number of data selected from various online public dataset, which are not specifically created for object detection purposes. Therefore, here, we aim to contribute to the field by releasing a hyperspectral salient object detection dataset with a collection of 60 hyperspectral images with their respective ground-truth binary images and representative rendered colour images (sRGB). We took several aspects in consideration during the data collection such as variation in object size, number of objects, foreground-background contrast, object position on the image, and etc. Then, we prepared ground truth binary images for each hyperspectral data, where salient objects are labelled on the images. Finally, we did performance evaluation using Area Under Curve (AUC) metric on some existing hyperspectral saliency detection models in literature.

cs.CV↗

arXiv2003

Secure direct communication using Einstein-Podolsky-Rosen pairs and teleportation

A novel scheme for secure direct communication between Alice and Bob is proposed, where there is no need for establishing a shared secret key. The communication is based on Einstein-Podolsky-Rosen pairs and teleportation between Alice and Bob. After insuring the security of the quantum channel (EPR pairs), Bob encodes the secret message directly on a sequence of particle states and transmits them to Alice by teleportation. In this scheme teleportation transmits Bob's message without revealing any information to a potential eavesdropper. Alice can read out the encoded messages directly by the measurement on her qubits. Because there is not a transmission of the qubit which carry the secret message between Alice and Bob, it is completely secure for direct secret communication if perfect quantum channel is used.

quant-ph↗