Summarizing a video requires a diverse understanding of the video, ranging from recognizing scenes to evaluating how much each frame is essential enough to be selected as a summary. Self-supervised learning (SSL) is acknowledged for its robustness and flexibility to multiple downstream tasks, but the video SSL has not shown its value for dense understanding tasks like video summarization. We claim an unsupervised autoencoder with sufficient self-supervised learning does not need any extra downstream architecture design or fine-tuning weights to be utilized as a video summarization model. The proposed method to evaluate the importance score of each frame takes advantage of the reconstruction score of the autoencoder's decoder. We evaluate the method in major unsupervised video summarization benchmarks to show its effectiveness under various experimental settings.
Temporal action detection aims to predict the time intervals and the classes of action instances in the video. Despite the promising performance, existing two-stream models exhibit slow inference speed due to their reliance on computationally expensive optical flow. In this paper, we introduce a decomposed cross-modal distillation framework to build a strong RGB-based detector by transferring knowledge of the motion modality. Specifically, instead of direct distillation, we propose to separately learn RGB and motion representations, which are in turn combined to perform action localization. The dual-branch design and the asymmetric training objectives enable effective motion knowledge transfer while preserving RGB information intact. In addition, we introduce a local attentive fusion to better exploit the multimodal complementarity. It is designed to preserve the local discriminability of the features that is important for action localization. Extensive experiments on the benchmarks verify the effectiveness of the proposed method in enhancing RGB-based action detectors. Notably, our framework is agnostic to backbones and detection heads, bringing consistent gains across different model combinations.
We introduce You Only Train Once (YOTO), a dynamic human generation framework, which performs free-viewpoint rendering of different human identities with distinct motions, via only one-time training from monocular videos. Most prior works for the task require individualized optimization for each input video that contains a distinct human identity, leading to a significant amount of time and resources for the deployment, thereby impeding the scalability and the overall application potential of the system. In this paper, we tackle this problem by proposing a set of learnable identity codes to expand the capability of the framework for multi-identity free-viewpoint rendering, and an effective pose-conditioned code query mechanism to finely model the pose-dependent non-rigid motions. YOTO optimizes neural radiance fields (NeRF) by utilizing designed identity codes to condition the model for learning various canonical T-pose appearances in a single shared volumetric representation. Besides, our joint learning of multiple identities within a unified model incidentally enables flexible motion transfer in high-quality photo-realistic renderings for all learned appearances. This capability expands its potential use in important applications, including Virtual Reality. We present extensive experimental results on ZJU-MoCap and PeopleSnapshot to clearly demonstrate the effectiveness of our proposed model. YOTO shows state-of-the-art performance on all evaluation metrics while showing significant benefits in training and inference efficiency as well as rendering quality. The code and model will be made publicly available soon.
Data augmentation has recently emerged as an essential component of modern training recipes for visual recognition tasks. However, data augmentation for video recognition has been rarely explored despite its effectiveness. Few existing augmentation recipes for video recognition naively extend the image augmentation methods by applying the same operations to the whole video frames. Our main idea is that the magnitude of augmentation operations for each frame needs to be changed over time to capture the real-world video's temporal variations. These variations should be generated as diverse as possible using fewer additional hyper-parameters during training. Through this motivation, we propose a simple yet effective video data augmentation framework, DynaAugment. The magnitude of augmentation operations on each frame is changed by an effective mechanism, Fourier Sampling that parameterizes diverse, smooth, and realistic temporal variations. DynaAugment also includes an extended search space suitable for video for automatic data augmentation methods. DynaAugment experimentally demonstrates that there are additional performance rooms to be improved from static augmentations on diverse video models. Specifically, we show the effectiveness of DynaAugment on various video datasets and tasks: large-scale video recognition (Kinetics-400 and Something-Something-v2), small-scale video recognition (UCF- 101 and HMDB-51), fine-grained video recognition (Diving-48 and FineGym), video action segmentation on Breakfast, video action localization on THUMOS'14, and video object detection on MOT17Det. DynaAugment also enables video models to learn more generalized representation to improve the model robustness on the corrupted videos.
To estimate the volume density and color of a 3D point in the multi-view image-based rendering, a common approach is to inspect the consensus existence among the given source image features, which is one of the informative cues for the estimation procedure. To this end, most of the previous methods utilize equally-weighted aggregation features. However, this could make it hard to check the consensus existence when some outliers, which frequently occur by occlusions, are included in the source image feature set. In this paper, we propose a novel source-view-wise feature aggregation method, which facilitates us to find out the consensus in a robust way by leveraging local structures in the feature set. We first calculate the source-view-wise distance distribution for each source feature for the proposed aggregation. After that, the distance distribution is converted to several similarity distributions with the proposed learnable similarity mapping functions. Finally, for each element in the feature set, the aggregation features are extracted by calculating the weighted means and variances, where the weights are derived from the similarity distributions. In experiments, we validate the proposed method on various benchmark datasets, including synthetic and real image scenes. The experimental results demonstrate that incorporating the proposed features improves the performance by a large margin, resulting in the state-of-the-art performance.
Managing the dynamic regions in the photometric loss formulation has been a main issue for handling the self-supervised depth estimation problem. Most previous methods have alleviated this issue by removing the dynamic regions in the photometric loss formulation based on the masks estimated from another module, making it difficult to fully utilize the training images. In this paper, to handle this problem, we propose an isometric self-sample-based learning (ISSL) method to fully utilize the training images in a simple yet effective way. The proposed method provides additional supervision during training using self-generated images that comply with pure static scene assumption. Specifically, the isometric self-sample generator synthesizes self-samples for each training image by applying random rigid transformations on the estimated depth. Thus both the generated self-samples and the corresponding training image always follow the static scene assumption. We show that plugging our ISSL module into several existing models consistently improves the performance by a large margin. In addition, it also boosts the depth accuracy over different types of scene, i.e., outdoor scenes (KITTI and Make3D) and indoor scene (NYUv2), validating its high effectiveness.
Joint object detection and online multi-object tracking (JDT) methods have been proposed recently to achieve one-shot tracking. Yet, existing works overlook the importance of detection itself and often result in missed detections when confronted by occlusions or motion blurs. The missed detections affect not only detection performance but also tracking performance due to inconsistent tracklets. Hence, we propose a new JDT model that recovers the missed detections while associating the detection candidates of consecutive frames by learning object-level spatio-temporal consistency through edge features in a Graph Neural Network (GNN). Our proposed model Sparse Graph Tracker (SGT) converts video data into a graph, where the nodes are top-$K$ scored detection candidates, and the edges are relations between the nodes at different times, such as position difference and visual similarity. Two nodes are connected if they are close in either a Euclidean or feature space, generating a sparsely connected graph. Without motion prediction or Re-Identification (ReID), the association is performed by predicting an edge score representing the probability that two connected nodes refer to the same object. Under the online setting, our SGT achieves state-of-the-art (SOTA) on the MOT17/20 Detection and MOT16/20 benchmarks in terms of AP and MOTA, respectively. Especially, SGT surpasses the previous SOTA on the crowded dataset MOT20 where partial occlusion cases are dominant, showing the effectiveness of detection recovery against partial occlusion. Code will be released at https://github.com/HYUNJS/SGT.
Recent self-supervised video representation learning methods focus on maximizing the similarity between multiple augmented views from the same video and largely rely on the quality of generated views. In this paper, we propose frequency augmentation (FreqAug), a spatio-temporal data augmentation method in the frequency domain for video representation learning. FreqAug stochastically removes undesirable information from the video by filtering out specific frequency components so that learned representation captures essential features of the video for various downstream tasks. Specifically, FreqAug pushes the model to focus more on dynamic features rather than static features in the video via dropping spatial or temporal low-frequency components. In other words, learning invariance between remaining frequency components results in high-frequency enhanced representation with less static bias. To verify the generality of the proposed method, we experiment with FreqAug on multiple self-supervised learning frameworks along with standard augmentations. Transferring the improved representation to five video action recognition and two temporal action localization downstream tasks shows consistent improvements over baselines.