Video temporal grounding aims to pinpoint a video segment that matches the query description. Despite the recent advance in short-form videos (\textit{e.g.}, in minutes), temporal grounding in long videos (\textit{e.g.}, in hours) is still at its early stage. To address this challenge, a common practice is to employ a sliding window, yet can be inefficient and inflexible due to the limited number of frames within the window. In this work, we propose an end-to-end framework for fast temporal grounding, which is able to model an hours-long video with \textbf{one-time} network execution. Our pipeline is formulated in a coarse-to-fine manner, where we first extract context knowledge from non-overlapped video clips (\textit{i.e.}, anchors), and then supplement the anchors that highly response to the query with detailed content knowledge. Besides the remarkably high pipeline efficiency, another advantage of our approach is the capability of capturing long-range temporal correlation, thanks to modeling the entire video as a whole, and hence facilitates more accurate grounding. Experimental results suggest that, on the long-form video datasets MAD and Ego4d, our method significantly outperforms state-of-the-arts, and achieves \textbf{14.6$\times$} / \textbf{102.8$\times$} higher efficiency respectively. Project can be found at \url{https://github.com/afcedf/SOONet.git}.
Sequential video understanding, as an emerging video understanding task, has driven lots of researchers' attention because of its goal-oriented nature. This paper studies weakly supervised sequential video understanding where the accurate time-stamp level text-video alignment is not provided. We solve this task by borrowing ideas from CLIP. Specifically, we use a transformer to aggregate frame-level features for video representation and use a pre-trained text encoder to encode the texts corresponding to each action and the whole video, respectively. To model the correspondence between text and video, we propose a multiple granularity loss, where the video-paragraph contrastive loss enforces matching between the whole video and the complete script, and a fine-grained frame-sentence contrastive loss enforces the matching between each action and its description. As the frame-sentence correspondence is not available, we propose to use the fact that video actions happen sequentially in the temporal domain to generate pseudo frame-sentence correspondence and supervise the network training with the pseudo labels. Extensive experiments on video sequence verification and text-to-video matching show that our method outperforms baselines by a large margin, which validates the effectiveness of our proposed approach. Code is available at https://github.com/svip-lab/WeakSVR
Communication load balancing aims to balance the load between different available resources, and thus improve the quality of service for network systems. After formulating the load balancing (LB) as a Markov decision process problem, reinforcement learning (RL) has recently proven effective in addressing the LB problem. To leverage the benefits of classical RL for load balancing, however, we need an explicit reward definition. Engineering this reward function is challenging, because it involves the need for expert knowledge and there lacks a general consensus on the form of an optimal reward function. In this work, we tackle the communication load balancing problem from an inverse reinforcement learning (IRL) approach. To the best of our knowledge, this is the first time IRL has been successfully applied in the field of communication load balancing. Specifically, first, we infer a reward function from a set of demonstrations, and then learn a reinforcement learning load balancing policy with the inferred reward function. Compared to classical RL-based solution, the proposed solution can be more general and more suitable for real-world scenarios. Experimental evaluations implemented on different simulated traffic scenarios have shown our method to be effective and better than other baselines by a considerable margin.
Time delay neural network (TDNN) has been proven to be efficient in learning discriminative speaker embeddings. One of its successful variant, ECAPA-TDNN, achieved state-of-the-art performance on speaker verification tasks at the cost of much higher computational complexity and slower inference speed. This makes it inadequate for scenarios with demanding inference rate and limited computational resources. We are thus interested in finding an architecture that can achieve the performance of ECAPA-TDNN and the efficiency of vanilla TDNN. In this paper, we propose an efficient network based on context-aware masking, namely CAM++, which uses densely connected time delay neural network (D-TDNN) as backbone and adopts a novel multi-granularity pooling to capture contextual information at different levels. Extensive experiments on two public benchmarks, VoxCeleb and CN-Celeb, demonstrate that the proposed architecture outperforms other mainstream speaker verification systems with lower computational cost and faster inference speed.
In this paper, we study the problem of temporal video grounding (TVG), which aims to predict the starting/ending time points of moments described by a text sentence within a long untrimmed video. Benefiting from fine-grained 3D visual features, the TVG techniques have achieved remarkable progress in recent years. However, the high complexity of 3D convolutional neural networks (CNNs) makes extracting dense 3D visual features time-consuming, which calls for intensive memory and computing resources. Towards efficient TVG, we propose a novel text-visual prompting (TVP) framework, which incorporates optimized perturbation patterns (that we call 'prompts') into both visual inputs and textual features of a TVG model. In sharp contrast to 3D CNNs, we show that TVP allows us to effectively co-train vision encoder and language encoder in a 2D TVG model and improves the performance of crossmodal feature fusion using only low-complexity sparse 2D visual features. The proposed prompts also compensate for the lack of spatiotemporal information in 2D CNNs for visual feature extraction. Further, we propose a TemporalDistance IoU (TDIoU) loss for efficient learning of TVG. Last but not least, extensive experiments on two benchmark datasets, Charades-STA and ActivityNet Captions datasets, empirically show that the proposed TVP significantly boosts the performance of 2D TVG (e.g., 9.79% improvement in Charades-STA and 30.77% improvement in ActivityNet Captions) and achieves 5x inference acceleration over TVG of using 3D visual features. Code and model will be released.
The COVID-19 pandemic has claimed millions of lives worldwide and elicited heightened emotions. This study examines the expression of various emotions pertaining to COVID-19 in the United States and India as manifested in over 54 million tweets, covering the fifteen-month period from February 2020 through April 2021, a period which includes the beginnings of the huge and disastrous increase in COVID-19 cases that started to ravage India in March 2021. Employing pre-trained emotion analysis and topic modeling algorithms, four distinct types of emotions (fear, anger, happiness, and sadness) and their time- and location-associated variations were examined. Results revealed significant country differences and temporal changes in the relative proportions of fear, anger, and happiness, with fear declining and anger and happiness fluctuating in 2020 until new situations over the first four months of 2021 reversed the trends. Detected differences are discussed briefly in terms of the latent topics revealed and through the lens of appraisal theories of emotions, and the implications of the findings are discussed.
Differentiable logics (DL) have recently been proposed as a method of training neural networks to satisfy logical specifications. A DL consists of a syntax in which specifications are stated and an interpretation function that translates expressions in the syntax into loss functions. These loss functions can then be used during training with standard gradient descent algorithms. The variety of existing DLs and the differing levels of formality with which they are treated makes a systematic comparative study of their properties and implementations difficult. This paper remedies this problem by suggesting a meta-language for defining DLs that we call the Logic of Differentiable Logics, or LDL. Syntactically, it generalises the syntax of existing DLs to FOL, and for the first time introduces the formalism for reasoning about vectors and learners. Semantically, it introduces a general interpretation function that can be instantiated to define loss functions arising from different existing DLs. We use LDL to establish several theoretical properties of existing DLs, and to conduct their empirical study in neural network verification.
Recently, mean field control (MFC) has provided a tractable and theoretically founded approach to otherwise difficult cooperative multi-agent control. However, the strict assumption of many independent, homogeneous agents may be too stringent in practice. In this work, we propose a novel discrete-time generalization of Markov decision processes and MFC to both many minor agents and potentially complex major agents -- major-minor mean field control (M3FC). In contrast to deterministic MFC, M3FC allows for stochastic minor agent distributions with strong correlation between minor agents through the major agent state, which can model arbitrary problem details not bound to any agent. Theoretically, we give rigorous approximation properties with novel proofs for both M3FC and existing MFC models in the finite multi-agent problem, together with a dynamic programming principle for solving such problems. In the infinite-horizon discounted case, existence of an optimal stationary policy follows. Algorithmically, we propose the major-minor mean field proximal policy optimization algorithm (M3FPPO) as a novel multi-agent reinforcement learning algorithm and demonstrate its success in illustrative M3FC-type problems.
As the size of the dataset used in deep learning tasks increases, the noisy label problem, which is a task of making deep learning robust to the incorrectly labeled data, has become an important task. In this paper, we propose a method of learning noisy label data using the label noise selection with test-time augmentation (TTA) cross-entropy and classifier learning with the NoiseMix method. In the label noise selection, we propose TTA cross-entropy by measuring the cross-entropy to predict the test-time augmented training data. In the classifier learning, we propose the NoiseMix method based on MixUp and BalancedMix methods by mixing the samples from the noisy and the clean label data. In experiments on the ISIC-18 public skin lesion diagnosis dataset, the proposed TTA cross-entropy outperformed the conventional cross-entropy and the TTA uncertainty in detecting label noise data in the label noise selection process. Moreover, the proposed NoiseMix not only outperformed the state-of-the-art methods in the classification performance but also showed the most robustness to the label noise in the classifier learning.
Developing low-cost and scalable security solutions is vital to the advent of future large-scale wireless networks. Traditional cryptographic methods fail to meet the low-latency and scalability requirements of these networks due to their computational and key management complexity. On the other hand, physical layer (PHY) security has been put forth as a cost-effective alternative to cryptographic mechanisms that can circumvent the need for explicit key exchange between communication devices, owing to the fact that PHY security relies on the physics of the signal transmission for providing security. In this work, we propose a space-time-modulated digitally-coded metamaterial (MTM) leaky wave antenna (LWA) that can enable PHY security by achieving the functionalities of directional modulation (DM). From the theoretical perspective, we first show how the proposed space-time MTM antenna architecture can achieve DM through both the spatial and spectral manipulation of the orthogonal frequency division multiplexing (OFDM) signal received by a user equipment (UE). Simulation results are then provided as proof-of-principle, demonstrating the applicability of our approach for achieving DM in various communication settings. To further validate our simulation results, we realize a prototype of the proposed architecture controlled by a field-programmable gate array (FPGA), which achieves DM via an optimized coding sequence carried out by the branch-and-bound algorithm corresponding to the states of the MTM LWA's unit cells. Experimental results confirm the theory behind the space-time-modulated MTM LWA in achieving DM, which is observed via both the spectral harmonic patterns and bit error rate (BER) measurements.