Vision transformer (ViT) has shown high potential in video recognition, owing to its flexible design, adaptable self-attention mechanisms, and the efficacy of masked pre-training. Yet, it still remains unclear how to adapt these pre-trained short-term ViTs for temporal action detection (TAD) in untrimmed videos. The existing works treat them as off-the-shelf feature extractors for each short trimmed snippet without capturing the fine-grained relation among different snippets in a broader temporal context. To mitigate this issue, this paper focuses on designing a new mechanism for adapting these pre-trained ViT models as a unified long-form video transformer to fully unleash its modeling power in capturing inter-snippet relation, while still keeping low computation overhead and memory consumption for efficient TAD. To this end, we design effective cross-snippet propagation modules to gradually exchange short-term video information among different snippets from two levels. For inner-backbone information propagation, we introduce a cross-snippet propagation strategy to enable multi-snippet temporal feature interaction inside the backbone. For post-backbone information propagation, we propose temporal transformer layers for further clip-level modeling. With the plain ViT-B pre-trained with VideoMAE, our end-to-end temporal action detector (ViT-TAD) yields a very competitive performance to previous temporal action detectors, riching up to 69.0 average mAP on THUMOS14, 37.12 average mAP on ActivityNet-1.3 and 17.20 average mAP on FineAction.
相關內容
The majority of the research on the quantization of Deep Neural Networks (DNNs) is focused on reducing the precision of tensors visible by high-level frameworks (e.g., weights, activations, and gradients). However, current hardware still relies on high-accuracy core operations. Most significant is the operation of accumulating products. This high-precision accumulation operation is gradually becoming the main computational bottleneck. This is because, so far, the usage of low-precision accumulators led to a significant degradation in performance. In this work, we present a simple method to train and fine-tune high-end DNNs, to allow, for the first time, utilization of cheaper, $12$-bits accumulators, with no significant degradation in accuracy. Lastly, we show that as we decrease the accumulation precision further, using fine-grained gradient approximations can improve the DNN accuracy.
Object tracking is central to robot perception and scene understanding. Tracking-by-detection has long been a dominant paradigm for object tracking of specific object categories. Recently, large-scale pre-trained models have shown promising advances in detecting and segmenting objects and parts in 2D static images in the wild. This begs the question: can we re-purpose these large-scale pre-trained static image models for open-vocabulary video tracking? In this paper, we re-purpose an open-vocabulary detector, segmenter, and dense optical flow estimator, into a model that tracks and segments objects of any category in 2D videos. Our method predicts object and part tracks with associated language descriptions in monocular videos, rebuilding the pipeline of Tractor with modern large pre-trained models for static image detection and segmentation: we detect open-vocabulary object instances and propagate their boxes from frame to frame using a flow-based motion model, refine the propagated boxes with the box regression module of the visual detector, and prompt an open-world segmenter with the refined box to segment the objects. We decide the termination of an object track based on the objectness score of the propagated boxes, as well as forward-backward optical flow consistency. We re-identify objects across occlusions using deep feature matching. We show that our model achieves strong performance on multiple established video object segmentation and tracking benchmarks, and can produce reasonable tracks in manipulation data. In particular, our model outperforms previous state-of-the-art in UVO and BURST, benchmarks for open-world object tracking and segmentation, despite never being explicitly trained for tracking. We hope that our approach can serve as a simple and extensible framework for future research.
Linear solvers are major computational bottlenecks in a wide range of decision support and optimization computations. The challenges become even more pronounced on heterogeneous hardware, where traditional sparse numerical linear algebra methods are often inefficient. For example, methods for solving ill-conditioned linear systems have relied on conditional branching, which degrades performance on hardware accelerators such as graphical processing units (GPUs). To improve the efficiency of solving ill-conditioned systems, our computational strategy separates computations that are efficient on GPUs from those that need to run on traditional central processing units (CPUs). Our strategy maximizes the reuse of expensive CPU computations. Iterative methods, which thus far have not been broadly used for ill-conditioned linear systems, play an important role in our approach. In particular, we extend ideas from [1] to implement iterative refinement using inexact LU factors and flexible generalized minimal residual (FGMRES), with the aim of efficient performance on GPUs. We focus on solutions that are effective within broader application contexts, and discuss how early performance tests could be improved to be more predictive of the performance in a realistic environment
Video Moment Retrieval (VMR) requires precise modelling of fine-grained moment-text associations to capture intricate visual-language relationships. Due to the lack of a diverse and generalisable VMR dataset to facilitate learning scalable moment-text associations, existing methods resort to joint training on both source and target domain videos for cross-domain applications. Meanwhile, recent developments in vision-language multimodal models pre-trained on large-scale image-text and/or video-text pairs are only based on coarse associations (weakly labelled). They are inadequate to provide fine-grained moment-text correlations required for cross-domain VMR. In this work, we solve the problem of unseen cross-domain VMR, where certain visual and textual concepts do not overlap across domains, by only utilising target domain sentences (text prompts) without accessing their videos. To that end, we explore generative video diffusion for fine-grained editing of source videos controlled by the target sentences, enabling us to simulate target domain videos. We address two problems in video editing for optimising unseen domain VMR: (1) generation of high-quality simulation videos of different moments with subtle distinctions, (2) selection of simulation videos that complement existing source training videos without introducing harmful noise or unnecessary repetitions. On the first problem, we formulate a two-stage video diffusion generation controlled simultaneously by (1) the original video structure of a source video, (2) subject specifics, and (3) a target sentence prompt. This ensures fine-grained variations between video moments. On the second problem, we introduce a hybrid selection mechanism that combines two quantitative metrics for noise filtering and one qualitative metric for leveraging VMR prediction on simulation video selection.
Personalized Federated Learning (PFL) has witnessed remarkable advancements, enabling the development of innovative machine learning applications that preserve the privacy of training data. However, existing theoretical research in this field has primarily focused on distributed optimization for minimization problems. This paper is the first to study PFL for saddle point problems encompassing a broader range of optimization problems, that require more than just solving minimization problems. In this work, we consider a recently proposed PFL setting with the mixing objective function, an approach combining the learning of a global model together with locally distributed learners. Unlike most previous work, which considered only the centralized setting, we work in a more general and decentralized setup that allows us to design and analyze more practical and federated ways to connect devices to the network. We proposed new algorithms to address this problem and provide a theoretical analysis of the smooth (strongly) convex-(strongly) concave saddle point problems in stochastic and deterministic cases. Numerical experiments for bilinear problems and neural networks with adversarial noise demonstrate the effectiveness of the proposed methods.
Mining users' intents plays a crucial role in sequential recommendation. The recent approach, ICLRec, was introduced to extract underlying users' intents using contrastive learning and clustering. While it has shown effectiveness, the existing method suffers from complex and cumbersome alternating optimization, leading to two main issues. Firstly, the separation of representation learning and clustering optimization within a generalized expectation maximization (EM) framework often results in sub-optimal performance. Secondly, performing clustering on the entire dataset hampers scalability for large-scale industry data. To address these challenges, we propose a novel intent learning method called \underline{ODCRec}, which integrates representation learning into an \underline{O}nline \underline{D}ifferentiable \underline{C}lustering framework for \underline{Rec}ommendation. Specifically, we encode users' behavior sequences and initialize the cluster centers as differentiable network parameters. Additionally, we design a clustering loss that guides the networks to differentiate between different cluster centers and pull similar samples towards their respective cluster centers. This allows simultaneous optimization of recommendation and clustering using mini-batch data. Moreover, we leverage the learned cluster centers as self-supervision signals for representation learning, resulting in further enhancement of recommendation performance. Extensive experiments conducted on open benchmarks and industry data validate the superiority, effectiveness, and efficiency of our proposed ODCRec method. Code is available at: //github.com/yueliu1999/ELCRec.
In practical communication systems, knowledge of channel models is often absent, and consequently, transceivers need be designed based on empirical data. In this work, we study data-driven approaches to reliably choosing decoding metrics and code rates that facilitate reliable communication over unknown discrete memoryless channels (DMCs). Our analysis is inspired by the PAC learning theory and does not rely on any assumptions on the statistical characteristics of DMCs. We show that a naive plug-in algorithm for choosing decoding metrics is likely to fail for finite training sets. We propose an alternative algorithm called the virtual sample algorithm and establish a non-asymptotic lower bound on its performance. The virtual sample algorithm is then used as a building block for constructing a learning algorithm that chooses a decoding metric and a code rate using which a transmitter and a receiver can reliably communicate at a rate arbitrarily close to the channel mutual information. Therefore, we conclude that DMCs are PAC learnable.
Multicast short video streaming can enhance bandwidth utilization by enabling simultaneous video transmission to multiple users over shared wireless channels. The existing network management schemes mainly rely on the sequential buffering principle and general quality of experience (QoE) model, which may deteriorate QoE when users' swipe behaviors exhibit distinct spatiotemporal variation. In this paper, we propose a digital twin (DT)-based network management scheme to enhance QoE. Firstly, user status emulated by the DT is utilized to estimate the transmission capabilities and watching probability distributions of sub-multicast groups (SMGs) for an adaptive segment buffering. The SMGs' buffers are aligned to the unique virtual buffers managed by the DT for a fine-grained buffer update. Then, a multicast QoE model consisting of rebuffering time, video quality, and quality variation is developed, by considering the mutual influence of segment buffering among SMGs. Finally, a joint optimization problem of segment version selection and slot division is formulated to maximize QoE. To efficiently solve the problem, a data-model-driven algorithm is proposed by integrating a convex optimization method and a deep reinforcement learning algorithm. Simulation results based on the real-world dataset demonstrate that the proposed DT-based network management scheme outperforms benchmark schemes in terms of QoE improvement.
Graph Neural Networks (GNN) has demonstrated the superior performance in many challenging applications, including the few-shot learning tasks. Despite its powerful capacity to learn and generalize from few samples, GNN usually suffers from severe over-fitting and over-smoothing as the model becomes deep, which limit the model scalability. In this work, we propose a novel Attentive GNN to tackle these challenges, by incorporating a triple-attention mechanism, \ie node self-attention, neighborhood attention, and layer memory attention. We explain why the proposed attentive modules can improve GNN for few-shot learning with theoretical analysis and illustrations. Extensive experiments show that the proposed Attentive GNN outperforms the state-of-the-art GNN-based methods for few-shot learning over the mini-ImageNet and Tiered-ImageNet datasets, with both inductive and transductive settings.
Named entity recognition (NER) is the task to identify text spans that mention named entities, and to classify them into predefined categories such as person, location, organization etc. NER serves as the basis for a variety of natural language applications such as question answering, text summarization, and machine translation. Although early NER systems are successful in producing decent recognition accuracy, they often require much human effort in carefully designing rules or features. In recent years, deep learning, empowered by continuous real-valued vector representations and semantic composition through nonlinear processing, has been employed in NER systems, yielding stat-of-the-art performance. In this paper, we provide a comprehensive review on existing deep learning techniques for NER. We first introduce NER resources, including tagged NER corpora and off-the-shelf NER tools. Then, we systematically categorize existing works based on a taxonomy along three axes: distributed representations for input, context encoder, and tag decoder. Next, we survey the most representative methods for recent applied techniques of deep learning in new NER problem settings and applications. Finally, we present readers with the challenges faced by NER systems and outline future directions in this area.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191