48 accepted papers
Unsupervised learning of latent motion from Internet videos is crucial for robot learning. Existing discrete methods generally mitigate the shortcut learning caused by extracting excessive static backgrounds through vector quantization with a small codebook size. However, they suffer from informatio
Image Super-Resolution (SR) aims to reconstruct high-resolution images from degraded low-resolution inputs. While diffusion-based SR methods offer powerful generative capabilities, their performance heavily depends on how semantic priors are structured and integrated into the generation process. Exi
The quadratic complexity of the attention mechanism severely limits the context scalability of Video Diffusion Transformers (DiTs). We find that the highly sparse spatio-temporal attention patterns exhibited in Video DiTs can be naturally represented by the Monarch matrix. It is a class of structure
Transformer-based methods have demonstrated impressive performance in low-level visual tasks such as Image Super-Resolution (SR). However, its computational complexity grows quadratically with the spatial resolution. A series of works attempt to alleviate this problem by dividing Low-Resolution imag…
Binaural audio enriches immersive experiences by enabling the perception of the spatial locations of sounding objects in AR, VR, and embodied AI applications. While existing audio spatialization methods can generally map any available monaural audio to binaural audio signals, they often lack the fle…
Image-to-video generation has made remarkable progress with the advancements in diffusion models, yet generating videos with realistic motion remains highly challenging. This difficulty arises from the complexity of accurately modeling motion, which involves capturing physical constraints, object in…
Video speaking style recognition (VSSR) aims to classify different types of conversations in videos, contributing significantly to understanding human interactions. A significant challenge in VSSR is the inherent similarity among conversation videos, which makes it difficult to distinguish between d…
Learning from multiple domains is a primary factor that influences the generalization of a single unified robot system. In this paper, we aim to learn the trajectory prediction model by using broad out-of-domain data to improve its performance and generalization ability. Trajectory model is designed…
Pre-trained vision-language models (VLMs) have shown impressive results in various visual classification tasks. However, we often fail to fully unleash their potential when adapting them for new concept understanding due to limited information on new classes. To address this limitation, we introduce…
Self-supervised foundation models have shown great potential in computer vision thanks to the pre-training paradigm of masked autoencoding. Scale is a primary factor influencing the performance of these foundation models. However these large foundation models often result in high computational cost.…
Temporal Action Detection (TAD) aims to identify the action boundaries and the corresponding category within untrimmed videos. Inspired by the success of DETR in object detection several methods have adapted the query-based framework to the TAD task. However these approaches primarily followed DETR…
"In recent years, 2D human pose estimation has made significant progress on public benchmarks. However, many of these approaches face challenges of less applicability in the industrial community due to the large number of parametric quantities and computational overhead. Efficient human pose estimat…
Lane detection is to determine the precise location and shape of lanes on the road. Despite efforts made by current methods, it remains a challenging task due to the complexity of real-world scenarios. Existing approaches, whether proposal-based or keypoint-based, suffer from depicting lanes effecti…
Video-based visual relation detection tasks such as video scene graph generation play important roles in fine-grained video understanding. However current video visual relation detection datasets have two main limitations that hinder the progress of research in this area. First they do not explore c…
Current RGB-D scene recognition approaches often train two standalone backbones for RGB and depth modalities with the same Places or ImageNet pre-training. However, the pre-trained depth network is still biased by RGB-based models which may result in a suboptimal solution. In this paper, we present…
Streaming video clips with large-scale video tokens impede vision transformers (ViTs) for efficient recognition, especially in video action detection where sufficient spatiotemporal representations are required for precise actor identification. In this work, we propose an end-to-end framework for ef…
Effectively extracting inter-frame motion and appearance information is important for video frame interpolation (VFI). Previous works either extract both types of information in a mixed way or devise separate modules for each type of information, which lead to representation ambiguity and low effici…
Image super-resolution (SR) serves as a fundamental tool for the processing and transmission of multimedia data. Recently, Transformer-based models have achieved competitive performances in image SR. They divide images into fixed-size patches and apply self-attention on these patches to model long-r…
Extending the success of 2D Large Kernel to 3D perception is challenging due to: 1. the cubically-increasing overhead in processing 3D data; 2. the optimization difficulties from data scarcity and sparsity. Previous work has taken the first step to scale up the kernel size from 3x3x3 to 7x7x7 by int…
Transformer-based trackers have achieved strong accuracy on the standard benchmarks. However, their efficiency remains an obstacle to practical deployment on both GPU and CPU platforms. In this paper, to overcome this issue, we propose a fully transformer tracking framework, coined as \emph{MixForme…
Object modeling has become a core part of recent tracking frameworks. Current popular tackers use Transformer attention to extract the template feature separately or interactively with the search region. However, separate template learning lacks communication between the template and search regions,…
Traditional video action detectors typically adopt the two-stage pipeline, where a person detector is first employed to yield actor boxes and then 3D RoIAlign is used to extract actor-specific features for classification. This detection paradigm requires multi-stage training and inference and cannot…
Multi-object tracking (MOT) in sports scenes plays a critical role in gathering players statistics, supporting further applications, such as automatic tactical analysis. Yet existing MOT benchmarks cast little attention on this domain. In this work, we present a new large-scale multi-object tracking…
Video Frame Interpolation (VFI) aims to synthesize non-existent intermediate frames between existent frames. Flow-based VFI algorithms estimate intermediate motion fields to warp the existent frames. Real-world motions' complexity and the reference frame's absence make motion estimation challenging.…
Existing CNN-based methods for image compression extract features through serially connected high-to-low (encoder) or low-to-high (decoder) resolution stages, leading to insufficient utilization of hierarchical features. To solve this problem, we present a hierarchical feature aggregation network (H…
Tracking often uses a multi-stage pipeline of feature extraction, target information integration, and bounding box estimation. To simplify this pipeline and unify the process of feature extraction and target information integration, we present a compact tracking framework, termed as MixFormer, built…
Temporal grounding aims to localize a video moment which is semantically aligned with a given natural language query. Existing methods typically apply a detection or regression pipeline on the fused representation with the research focus on designing complicated prediction heads or fusion strategies…
Recently, convolutional neural network (CNN) has made a mighty advance in image super-resolution (SR). Most recent models exploit attention mechanism (AM) to focus on high-frequency information. However, these methods exclusively consider interdependencies among channels or spatials, leading to equa…
Recent convolution neural networks (CNNs) have achieved remarkable success in lightweight image super-resolution (LISR). The goal of LISR is to restore more accurate details with less model capacity. However, we observe two phenomena in current micro-architectures, one is the lack of consistent lear…
Previous point cloud semantic segmentation networks use the same process to aggregate features from neighbors of the same category and different categories. However, the joint area between two objects usually only occupies a small percentage in the whole scene. Thus the networks are well-trained for…
Anomaly detection is the task of identifying unusual samples in data. Typically anomaly detection is defined on an unlabeled dataset that is assumed most of the samples are normal and others are anomalies. However, in industrial practice, one may have access to a part of annotated data. This gives u…
Recent research on human pose estimation has achieved significant improvement. However, most existing methods tend to pursue higher scores on benchmark datasets using complex architecture, ignoring the deployment costs in practice. In this paper, we investigate the problem of lightweight human pose…
Frame sampling is a fundamental problem in video action recognition due to the essential redundancy in time and limited computation resources. The existing sampling strategy often employs a fixed frame selection and lacks the flexibility to deal with complex variations in videos. In this paper, we p…
Spatio-temporal action detection is an important and challenging problem in video understanding. The existing action detection benchmarks are limited in aspects of small numbers of instances in a trimmed video or low-level atomic actions. This paper aims to present a new multi-person dataset of spat…
The classification and regression head are both indispensable components to build up a dense object detector, which are usually supervised by the same training samples and thus expected to have consistency with each other for detecting objects accurately in final detection pipelines. In this paper,…
Temporal action proposal generation is an important and challenging task in video understanding, which aims at detecting all temporal segments containing action instances of interest. The existing proposal generation approaches are generally based on pre-defined anchor windows or heuristic bottom-up…
Deep learning has achieved remarkable progress for visual recognition on large-scale balanced datasets but still performs poorly on real-world long-tailed data. Previous methods often adopt class re-balanced training strategies to effectively alleviate the imbalance issue, but might be a risk of ove…
Temporal modeling still remains challenging for action recognition in videos. To mitigate this issue, this paper presents a new video architecture, termed as Temporal Difference Network (TDN), with a focus on capturing multi-scale temporal information for efficient action recognition. The core of ou…
This paper deals with a challenging task of video scene graph generation (VidSGG), which could serve as a structured video representation for high-level understanding tasks. We present a new detect-to-track paradigm for this task by decoupling the context modeling for relation prediction from the co…
The existing action tubelet detectors often depend on heuristic anchor design and placement, which might be computationally expensive and sub-optimal for precise localization. In this paper, we present a conceptually simple, computationally efficient, and more precise action tubelet detection framew…
Identifying human action segments in an untrimmed video is still challenging due to boundary ambiguity and over-segmentation issues. To address these problems, we present a new boundary-aware cascade network by introducing two novel components. First, we devise a new cascading paradigm, called Stage…
Video action detection approaches usually conduct actor-centric action recognition over RoI-pooled features following the standard pipeline of Faster-RCNN. In this work, we first empirically find the recognition accuracy is highly correlated with the bounding box size of an actor, and thus higher re…
Recently, deep convolutional neural networks (CNNs) have made remarkable progress on single image super-resolution (SISR). However, many of these methods use very deep or wide convolutional layers to achieve good performance, which treat all feature channels indiscriminately and neglect the differen…
Recently, very deep convolutional neural networks (CNNs) have shown great power in single image super-resolution (SISR) and achieved significant improvements against traditional methods. Among these CNN-based methods, the residual connections play a critical role in boosting the network performance.…
Spatial downsampling layers are favored in convolutional neural networks (CNNs) to downscale feature maps for larger receptive fields and less memory consumption. However, for discriminative tasks, there is a possibility that these layers lose the discriminative details due to improper pooling strat…
Modeling relation between actors is important for recognizing group activity in a multi-person scene. This paper aims at learning discriminative relation between actors efficiently using deep models. To this end, we propose to build a flexible and efficient \rm Actor Relation Graph (ARG) to simult…
Cross-modal transfer is helpful to enhance modality-specific discriminative power for scene recognition. To this end, this paper presents a unified framework to integrate the tasks of cross-modal translation and modality-specific recognition, termed as Translate-to-Recognize Network TRecgNet. Specif…
Consistent object extraction plays an essential role for stereo image editing with the population of stereoscopic 3D media. Most previous methods perform segmentation on entire images for both views using dense stereo correspondence constraints. We find that for such kind of methods the computation…