arXiv subjects

Xiaohan Wang

Publications and source records attributed to Xiaohan Wang.

At least 145 records · Page 8Linked to original sources

arXiv2023

Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models

Vision-language models (VLMs) pre-trained on large-scale image-text pairs have demonstrated impressive transferability on various visual tasks. Transferring knowledge from such powerful VLMs is a promising direction for building effective video recognition models. However, current exploration in this field is still limited. We believe that the greatest value of pre-trained VLMs lies in building a bridge between visual and textual domains. In this paper, we propose a novel framework called BIKE, which utilizes the cross-modal bridge to explore bidirectional knowledge: i) We introduce the Video Attribute Association mechanism, which leverages the Video-to-Text knowledge to generate textual auxiliary attributes for complementing video recognition. ii) We also present a Temporal Concept Spotting mechanism that uses the Text-to-Video expertise to capture temporal saliency in a parameter-free manner, leading to enhanced video representation. Extensive studies on six popular video datasets, including Kinetics-400 & 600, UCF-101, HMDB-51, ActivityNet and Charades, show that our method achieves state-of-the-art performance in various recognition scenarios, such as general, zero-shot, and few-shot video recognition. Our best model achieves a state-of-the-art accuracy of 88.6% on the challenging Kinetics-400 using the released CLIP model. The code is available at https://github.com/whwu95/BIKE .

cs.CV↗

arXiv2023

Lana: A Language-Capable Navigator for Instruction Following and Generation

Recently, visual-language navigation (VLN) -- entailing robot agents to follow navigation instructions -- has shown great advance. However, existing literature put most emphasis on interpreting instructions into actions, only delivering "dumb" wayfinding agents. In this article, we devise LANA, a language-capable navigation agent which is able to not only execute human-written navigation commands, but also provide route descriptions to humans. This is achieved by simultaneously learning instruction following and generation with only one single model. More specifically, two encoders, respectively for route and language encoding, are built and shared by two decoders, respectively, for action prediction and instruction generation, so as to exploit cross-task knowledge and capture task-specific characteristics. Throughout pretraining and fine-tuning, both instruction following and generation are set as optimization objectives. We empirically verify that, compared with recent advanced task-specific solutions, LANA attains better performances on both instruction following and route description, with nearly half complexity. In addition, endowed with language generation capability, LANA can explain to humans its behaviors and assist human's wayfinding. This work is expected to foster future efforts towards building more trustworthy and socially-intelligent navigation robots.

cs.CV↗

arXiv2023

Quantifying the uneven efficiency benefits of ridesharing market integration

Ridesharing is recognized as one of the key pathways to sustainable urban mobility. With the emergence of Transportation Network Companies (TNCs) such as Uber and Lyft, the ridesharing market has become increasingly fragmented in many cities around the world, leading to efficiency loss and increased traffic congestion. While an integrated ridesharing market (allowing sharing across TNCs) can improve the overall efficiency, how such benefits may vary across TNCs based on actual market characteristics is still not well understood. In this study, we extend a shareability network framework to quantify and explain the efficiency benefits of ridesharing market integration using available TNC trip records. Through a case study in Manhattan, New York City, the proposed framework is applied to analyze a real-world ridesharing market with 3 TNCs$-$Uber, Lyft, and Via. It is estimated that a perfectly integrated market in Manhattan would improve ridesharing efficiency by 13.3%, or 5% of daily TNC vehicle hours traveled. Further analysis reveals that (1) the efficiency improvement is negatively correlated with the overall demand density and inter-TNC spatiotemporal unevenness (measured by network modularity), (2) market integration would generate a larger efficiency improvement in a competitive market, and (3) the TNC with a higher intra-TNC demand concentration (measured by clustering coefficient) would benefit less from market integration. As the uneven benefits may deter TNCs from collaboration, we also illustrate how to quantify each TNC's marginal contribution based on the Shapley value, which can be used to ensure equitable profit allocation. These results can help market regulators and business alliances to evaluate and monitor market efficiency and dynamically adjust their strategies, incentives, and profit allocation schemes to promote market integration and collaboration.

physics.soc-ph↗

arXiv2022

Automated turnkey microcomb for low-noise microwave synthesis

Microresonator-based optical frequency comb (microcomb) has the potential to revolutionize the accuracy of frequency synthesizer in radar and communication applications. However, fundamental limit exists for low noise microcomb generation, especially in low size, weight, power and cost (SWaP-C) package. Here we resolve this limit, by the demonstration of an automated turnkey microcomb, operating close to its low quantum-limited phase noise, within a compact setup size of 85 mm * 90 mm * 25 mm. High quality factor fiber Fabry-Perot resonator (FFPR), with Q up to 4.0 * 10^9, is the key for both low quantum noise and pump noise limit, in the diode-pump case in a self-injection locking scheme. Low phase noise of -80 and -105 dBc/Hz at 100 Hz, -106 and -125 dBc/Hz at 1 kHz, -133 and -148 dBc/Hz at 10 kHz is achieved at 10.1 GHz and 1.7 GHz repetition frequencies, respectively. With the simultaneous automated turnkey, low-noise and direct-diode-pump capability, our microcomb is ready to be used as a low-noise frequency synthesizer with low SWaP-C and thus field deployability.

physics.optics↗

arXiv2022

Measuring quantum geometric tensor of non-Abelian system in superconducting circuits

Topology played an important role in physics research during the last few decades. In particular, the quantum geometric tensor that provides local information about topological properties has attracted much attention. It will reveal interesting topological properties in non-Abelian systems, which have not been realized in practice. Here, we use a four-qubit quantum system in superconducting circuits to construct a degenerate Hamiltonian with parametric modulation. By manipulating the Hamiltonian with periodic drivings, we simulate the Bernevig-Hughes-Zhang model and obtain the quantum geometric tensor from interference oscillation. In addition, we reveal its topological feature by extracting the topological invariant, demonstrating an effective protocol for quantum simulation of a non-Abelian system.

quant-ph↗

arXiv2022

Self-supervised Point Cloud Representation Learning via Separating Mixed Shapes

The manual annotation for large-scale point clouds costs a lot of time and is usually unavailable in harsh real-world scenarios. Inspired by the great success of the pre-training and fine-tuning paradigm in both vision and language tasks, we argue that pre-training is one potential solution for obtaining a scalable model to 3D point cloud downstream tasks as well. In this paper, we, therefore, explore a new self-supervised learning method, called Mixing and Disentangling (MD), for 3D point cloud representation learning. As the name implies, we mix two input shapes and demand the model learning to separate the inputs from the mixed shape. We leverage this reconstruction task as the pretext optimization objective for self-supervised learning. There are two primary advantages: 1) Compared to prevailing image datasets, eg, ImageNet, point cloud datasets are de facto small. The mixing process can provide a much larger online training sample pool. 2) On the other hand, the disentangling process motivates the model to mine the geometric prior knowledge, eg, key points. To verify the effectiveness of the proposed pretext task, we build one baseline network, which is composed of one encoder and one decoder. During pre-training, we mix two original shapes and obtain the geometry-aware embedding from the encoder, then an instance-adaptive decoder is applied to recover the original shapes from the embedding. Albeit simple, the pre-trained encoder can capture the key points of an unseen point cloud and surpasses the encoder trained from scratch on downstream tasks. The proposed method has improved the empirical performance on both ModelNet-40 and ShapeNet-Part datasets in terms of point cloud classification and segmentation tasks. We further conduct ablation studies to explore the effect of each component and verify the generalization of our proposed strategy by harnessing different backbones.

cs.CV↗

arXiv2022

ReLER@ZJU-Alibaba Submission to the Ego4D Natural Language Queries Challenge 2022

In this report, we present the ReLER@ZJU-Alibaba submission to the Ego4D Natural Language Queries (NLQ) Challenge in CVPR 2022. Given a video clip and a text query, the goal of this challenge is to locate a temporal moment of the video clip where the answer to the query can be obtained. To tackle this task, we propose a multi-scale cross-modal transformer and a video frame-level contrastive loss to fully uncover the correlation between language queries and video clips. Besides, we propose two data augmentation strategies to increase the diversity of training samples. The experimental results demonstrate the effectiveness of our method. The final submission ranked first on the leaderboard.

cs.CV↗

arXiv2022

Jointly Harnessing Prior Structures and Temporal Consistency for Sign Language Video Generation

Sign language is the window for people differently-abled to express their feelings as well as emotions. However, it remains challenging for people to learn sign language in a short time. To address this real-world challenge, in this work, we study the motion transfer system, which can transfer the user photo to the sign language video of specific words. In particular, the appearance content of the output video comes from the provided user image, while the motion of the video is extracted from the specified tutorial video. We observe two primary limitations in adopting the state-of-the-art motion transfer methods to sign language generation:(1) Existing motion transfer works ignore the prior geometrical knowledge of the human body. (2) The previous image animation methods only take image pairs as input in the training stage, which could not fully exploit the temporal information within videos. In an attempt to address the above-mentioned limitations, we propose Structure-aware Temporal Consistency Network (STCNet) to jointly optimize the prior structure of human with the temporal consistency for sign language video generation. There are two main contributions in this paper. (1) We harness a fine-grained skeleton detector to provide prior knowledge of the body keypoints. In this way, we ensure the keypoint movement in a valid range and make the model become more explainable and robust. (2) We introduce two cycle-consistency losses, i.e., short-term cycle loss and long-term cycle loss, which are conducted to assure the continuity of the generated video. We optimize the two losses and keypoint detector network in an end-to-end manner.

cs.CV↗

arXiv2022

CenterCLIP: Token Clustering for Efficient Text-Video Retrieval

Recently, large-scale pre-training methods like CLIP have made great progress in multi-modal research such as text-video retrieval. In CLIP, transformers are vital for modeling complex multi-modal relations. However, in the vision transformer of CLIP, the essential visual tokenization process, which produces discrete visual token sequences, generates many homogeneous tokens due to the redundancy nature of consecutive and similar frames in videos. This significantly increases computation costs and hinders the deployment of video retrieval models in web applications. In this paper, to reduce the number of redundant video tokens, we design a multi-segment token clustering algorithm to find the most representative tokens and drop the non-essential ones. As the frame redundancy occurs mostly in consecutive frames, we divide videos into multiple segments and conduct segment-level clustering. Center tokens from each segment are later concatenated into a new sequence, while their original spatial-temporal relations are well maintained. We instantiate two clustering algorithms to efficiently find deterministic medoids and iteratively partition groups in high dimensional space. Through this token clustering and center selection procedure, we successfully reduce computation costs by removing redundant visual tokens. This method further enhances segment-level semantic alignment between video and text representations, enforcing the spatio-temporal interactions of tokens from within-segment frames. Our method, coined as CenterCLIP, surpasses existing state-of-the-art by a large margin on typical text-video benchmarks, while reducing the training memory cost by 35\% and accelerating the inference speed by 14\% at the best case. The code is available at \href{https://github.com/mzhaoshuai/CenterCLIP}{https://github.com/mzhaoshuai/CenterCLIP}.

cs.CV↗

arXiv2022

Multi-robot Cooperative Pursuit via Potential Field-Enhanced Reinforcement Learning

It is of great challenge, though promising, to coordinate collective robots for hunting an evader in a decentralized manner purely in light of local observations. In this paper, this challenge is addressed by a novel hybrid cooperative pursuit algorithm that combines reinforcement learning with the artificial potential field method. In the proposed algorithm, decentralized deep reinforcement learning is employed to learn cooperative pursuit policies that are adaptive to dynamic environments. The artificial potential field method is integrated into the learning process as predefined rules to improve the data efficiency and generalization ability. It is shown by numerical simulations that the proposed hybrid design outperforms the pursuit policies either learned from vanilla reinforcement learning or designed by the potential field method. Furthermore, experiments are conducted by transferring the learned pursuit policies into real-world mobile robots. Experimental results demonstrate the feasibility and potential of the proposed algorithm in learning multiple cooperative pursuit strategies.

cs.RO↗

arXiv2022

Action Keypoint Network for Efficient Video Recognition

Reducing redundancy is crucial for improving the efficiency of video recognition models. An effective approach is to select informative content from the holistic video, yielding a popular family of dynamic video recognition methods. However, existing dynamic methods focus on either temporal or spatial selection independently while neglecting a reality that the redundancies are usually spatial and temporal, simultaneously. Moreover, their selected content is usually cropped with fixed shapes, while the realistic distribution of informative content can be much more diverse. With these two insights, this paper proposes to integrate temporal and spatial selection into an Action Keypoint Network (AK-Net). From different frames and positions, AK-Net selects some informative points scattered in arbitrary-shaped regions as a set of action keypoints and then transforms the video recognition into point cloud classification. AK-Net has two steps, i.e., the keypoint selection and the point cloud classification. First, it inputs the video into a baseline network and outputs a feature map from an intermediate layer. We view each pixel on this feature map as a spatial-temporal point and select some informative keypoints using self-attention. Second, AK-Net devises a ranking criterion to arrange the keypoints into an ordered 1D sequence. Consequentially, AK-Net brings two-fold benefits for efficiency: The keypoint selection step collects informative content within arbitrary shapes and increases the efficiency for modeling spatial-temporal dependencies, while the point cloud classification step further reduces the computational cost by compacting the convolutional kernels. Experimental results show that AK-Net can consistently improve the efficiency and performance of baseline methods on several video recognition benchmarks.

cs.CV↗

arXiv2021

Optimal control of stimulated Raman adiabatic passage in a superconducting qudit

Stimulated Raman adiabatic passage (STIRAP) is a widely used protocol to realize high-fidelity and robust quantum control in various quantum systems. However, further application of this protocol in superconducting qubits is limited by population leakage caused by the only weak anharmonicity. Here we introduce an optimally controlled shortcut-to-adiabatic (STA) technique to speed up the STIRAP protocol in a superconducting qudit. By modifying the shapes of the STIRAP pulses, we experimentally realize a fast (32 ns) and high-fidelity quantum state transfer. In addition, we demonstrate that our protocol is robust against control parameter perturbations. Our stimulated Raman shortcut-to-adiabatic passage transition provides an efficient and practical approach for quantum information processing.

quant-ph↗

arXiv2021

PR-RRN: Pairwise-Regularized Residual-Recursive Networks for Non-rigid Structure-from-Motion

We propose PR-RRN, a novel neural-network based method for Non-rigid Structure-from-Motion (NRSfM). PR-RRN consists of Residual-Recursive Networks (RRN) and two extra regularization losses. RRN is designed to effectively recover 3D shape and camera from 2D keypoints with novel residual-recursive structure. As NRSfM is a highly under-constrained problem, we propose two new pairwise regularization to further regularize the reconstruction. The Rigidity-based Pairwise Contrastive Loss regularizes the shape representation by encouraging higher similarity between the representations of high-rigidity pairs of frames than low-rigidity pairs. We propose minimum singular-value ratio to measure the pairwise rigidity. The Pairwise Consistency Loss enforces the reconstruction to be consistent when the estimated shapes and cameras are exchanged between pairs. Our approach achieves state-of-the-art performance on CMU MOCAP and PASCAL3D+ dataset.

cs.CV↗

arXiv2021

Less is More: Sparse Sampling for Dense Reaction Predictions

Obtaining viewer responses from videos can be useful for creators and streaming platforms to analyze the video performance and improve the future user experience. In this report, we present our method for 2021 Evoked Expression from Videos Challenge. In particular, our model utilizes both audio and image modalities as inputs to predict emotion changes of viewers. To model long-range emotion changes, we use a GRU-based model to predict one sparse signal with 1Hz. We observe that the emotion changes are smooth. Therefore, the final dense prediction is obtained via linear interpolating the signal, which is robust to the prediction fluctuation. Albeit simple, the proposed method has achieved pearson's correlation score of 0.04430 on the final private test set.

cs.CV↗

arXiv2021

Connecting Language and Vision for Natural Language-Based Vehicle Retrieval

Vehicle search is one basic task for the efficient traffic management in terms of the AI City. Most existing practices focus on the image-based vehicle matching, including vehicle re-identification and vehicle tracking. In this paper, we apply one new modality, i.e., the language description, to search the vehicle of interest and explore the potential of this task in the real-world scenario. The natural language-based vehicle search poses one new challenge of fine-grained understanding of both vision and language modalities. To connect language and vision, we propose to jointly train the state-of-the-art vision models with the transformer-based language model in an end-to-end manner. Except for the network structure design and the training strategy, several optimization objectives are also re-visited in this work. The qualitative and quantitative experiments verify the effectiveness of the proposed method. Our proposed method has achieved the 1st place on the 5th AI City Challenge, yielding competitive performance 18.69% MRR accuracy on the private test set. We hope this work can pave the way for the future study on using language description effectively and efficiently for real-world vehicle retrieval systems. The code will be available at https://github.com/ShuaiBai623/AIC2021-T5-CLV.

cs.CV↗

arXiv2021

T2VLAD: Global-Local Sequence Alignment for Text-Video Retrieval

Text-video retrieval is a challenging task that aims to search relevant video contents based on natural language descriptions. The key to this problem is to measure text-video similarities in a joint embedding space. However, most existing methods only consider the global cross-modal similarity and overlook the local details. Some works incorporate the local comparisons through cross-modal local matching and reasoning. These complex operations introduce tremendous computation. In this paper, we design an efficient global-local alignment method. The multi-modal video sequences and text features are adaptively aggregated with a set of shared semantic centers. The local cross-modal similarities are computed between the video feature and text feature within the same center. This design enables the meticulous local comparison and reduces the computational cost of the interaction between each text-video pair. Moreover, a global alignment method is proposed to provide a global cross-modal measurement that is complementary to the local perspective. The global aggregated visual features also provide additional supervision, which is indispensable to the optimization of the learnable semantic centers. We achieve consistent improvements on three standard text-video retrieval benchmarks and outperform the state-of-the-art by a clear margin.

cs.CV↗

arXiv2021

Learning to Anticipate Egocentric Actions by Imagination

Anticipating actions before they are executed is crucial for a wide range of practical applications, including autonomous driving and robotics. In this paper, we study the egocentric action anticipation task, which predicts future action seconds before it is performed for egocentric videos. Previous approaches focus on summarizing the observed content and directly predicting future action based on past observations. We believe it would benefit the action anticipation if we could mine some cues to compensate for the missing information of the unobserved frames. We then propose to decompose the action anticipation into a series of future feature predictions. We imagine how the visual feature changes in the near future and then predicts future action labels based on these imagined representations. Differently, our ImagineRNN is optimized in a contrastive learning way instead of feature regression. We utilize a proxy task to train the ImagineRNN, i.e., selecting the correct future states from distractors. We further improve ImagineRNN by residual anticipation, i.e., changing its target to predicting the feature difference of adjacent frames instead of the frame content. This promotes the network to focus on our target, i.e., the future action, as the difference between adjacent frame features is more important for forecasting the future. Extensive experiments on two large-scale egocentric action datasets validate the effectiveness of our method. Our method significantly outperforms previous methods on both the seen test set and the unseen test set of the EPIC Kitchens Action Anticipation Challenge.

cs.CV↗

arXiv2020

Ultra-bright multiplexed energy-time entangled photon generation from lithium niobate on insulator chip

High-flux entangled photon source is the key resource for quantum optical study and application. Here it is realized in a lithium niobate on isolator (LNOI) chip, with 2.79*10^11 Hz/mW photon pair rate and 1.53*10^9 Hz/nm/mW spectral brightness. These data are boosted by over two orders of magnitude compared to existing technologies. A 130-nm broad bandwidth is engineered for 8-channel multiplexed energy-time entanglement. Harnessed by high-extinction frequency correlation and Franson interferences up to 99.17% visibility, such energy-time entanglement multiplexing further enhances high-flux data rate, and warrants broad applications in quantum information processing on a chip.

quant-ph↗