Transformers have proven superior performance for a wide variety of tasks since they were introduced. In recent years, they have drawn attention from the vision community in tasks such as image classification and object detection. Despite this wave, an accurate and efficient multiple-object tracking (MOT) method based on transformers is yet to be designed. We argue that the direct application of a transformer architecture with quadratic complexity and insufficient noise-initialized sparse queries – is not optimal for MOT. We propose TransCenter, a transformer-based MOT architecture with dense representations for accurately tracking all the objects while keeping a reasonable runtime. Methodologically, we propose the use of image-related dense detection queries and efficient sparse tracking queries produced by our carefully designed query learning networks (QLN). On one hand, the dense image-related detection queries allow us to infer targets’ locations globally and robustly through dense heatmap outputs. On the other hand, the set of sparse tracking queries efficiently interacts with image features in our TransCenter Decoder to associate object positions through time. As a result, TransCenterexhibits remarkable performance improvements and outperforms by a large margin the current state-of-the-art methods in two standard MOT benchmarks with two tracking settings (public/private). TransCenter is also proven efficient and accurate by an extensive ablation study and, comparisons to more naive alternatives and concurrent works. The code is made publicly available at https://github.com/yihongxu/transcenter .

We focus on the task of generating sound from natural videos, and the sound should be both temporally and content-wise aligned with visual signals. This task is extremely challenging because some sounds generated outside a camera can not be inferred from video content. The model may be forced to learn an incorrect mapping between visual content and these irrelevant sounds. To address this challenge, we propose a framework named REGNET. In this framework, we first extract appearance and motion features from video frames to better distinguish the object that emits sound from complex background information. We then introduce an innovative audio forwarding regularizer that directly considers the real sound as input and outputs bottlenecked sound features. Using both visual and bottlenecked sound features for sound prediction during training provides stronger supervision for the sound prediction. The audio forwarding regularizer can control the irrelevant sound component and thus prevent the model from learning an incorrect mapping between video frames and sound emitted by the object that is out of the screen. During testing, the audio forwarding regularizer is removed to ensure that REGNET can produce purely aligned sound only from visual features. Extensive evaluations based on Amazon Mechanical Turk demonstrate that our method significantly improves both temporal and contentwise alignment. Remarkably, our generated sound can fool the human with a 68.12% success rate. Code and pre-trained models are publicly available at https://github.com/PeihaoChen/regnet.

We address the challenging problem of weakly supervised temporal action localization from unconstrained web videos, where only the video-level action labels are available during training. Inspired by the Adversarial Erasing strategy in weakly supervised semantic segmentation, we propose a novel iterative-winners-out network. Specifically, we make two technical contributions: 1) we propose an iterative training strategy, namely winners-out, to select the most discriminative action instances in each training iteration and remove them in the next training iteration. This iterative process alleviates the “winner-takes-all” phenomenon that existing approaches tend to choose the video segments that strongly correspond to the video label, but neglect other less discriminative video segments. With this strategy, our network is able to localize not only the most discriminative instances but also the less discriminative ones. 2) to better select the target action instances in winners-out, we devise a class-discriminative localization technique. By employing the attention mechanism and the information learned from data, our technique is able to identify the most discriminative action instances effectively. The two key components are integrated into an end-to-end network to localize actions without using the frame-level annotations. Extensive experimental results demonstrate that our method outperforms the state-of-the-art weakly supervised approaches on ActivityNet1.3 and improves mAP from 16.9% to 20.5% on THUMOS14. Notably, even with weak video-level supervision, our method attains comparable accuracy to those employing frame-level supervisions.

Despite the success of deep learning for static image understanding, it remains unclear what are the most effective network architectures for spatial-temporal modeling in videos. In this paper, in contrast to the existing CNN+RNN or pure 3D convolution based approaches, we explore a novel spatialtemporal network (StNet) architecture for both local and global modeling in videos. Particularly, StNet stacks N successive video frames into a super-image which has 3N channels and applies 2D convolution on super-images to capture local spatial-temporal relationship. To model global spatialtemporal structure, we apply temporal convolution on the local spatial-temporal feature maps. Specifically, a novel temporal Xception block is proposed in StNet, which employs a separate channel-wise and temporal-wise convolution over the feature sequence of a video. Extensive experiments on the Kinetics dataset demonstrate that our framework outperforms several state-of-the-art approaches in action recognition and can strike a satisfying trade-off between recognition accuracy and model complexity. We further demonstrate the generalization performance of the leaned video representations on the UCF101 dataset.

Temporal action localization, which aims at recognizing the location and the category of action instances in videos, has long been researched. Existing methods divide each video into multiple action units (i.e., proposals in two-stage methods and segments in one-stage methods) and then perform recognition/regression on each of them individually without explicitly exploiting their relations, which, however, play an important role in action localization. In this paper, we propose a general graph convolutional module (GCM) that can be easily plugged into existing action localization methods, including two-stage and one-stage paradigms. Specifically, we first construct a graph, where each action unit is represented as a node and their relations as edges. We use two types of relations, one for capturing the temporal connections, and the other one for characterizing the semantic relationship. Then, we apply graph convolutional networks (GCNs) on the graph to model the relations and learn more informative representations for action localization. Experimental results show that GCM consistently improves the performance of both two-stage action localization methods (e.g., CBR and R-C3D) and one-stage methods (e.g., D-SSAD), verifying the generality and effectiveness of GCM. Moreover, with the aid of GCM, our approach significantly outperforms the state-of-the-art on THUMOS14 and ActivityNet.