Related papers: AdaSpot: Spend Resolution Where It Matters for Pre…
Event cameras offer high temporal resolution and power efficiency, making them well-suited for edge AI applications. However, their high event rates present challenges for data transmission and processing. Subsampling methods provide a…
Complex reasoning problems contain states that vary in the computational cost required to determine a good action plan. Taking advantage of this property, we propose Adaptive Subgoal Search (AdaSubS), a search method that adaptively adjusts…
We introduce AdaSub, a stochastic optimization algorithm that computes a search direction based on second-order information in a low-dimensional subspace that is defined adaptively based on available current and past information. Compared…
Given a stream of heterogeneous graphs containing different types of nodes and edges, how can we spot anomalous ones in real-time while consuming bounded memory? This problem is motivated by and generalizes from its application in security…
Scene flow depicts the dynamics of a 3D scene, which is critical for various applications such as autonomous driving, robot navigation, AR/VR, etc. Conventionally, scene flow is estimated from dense/regular RGB video frames. With the…
The field of keypoint extraction, which is essential for vision applications like Structure from Motion (SfM) and Simultaneous Localization and Mapping (SLAM), has evolved from relying on handcrafted methods to leveraging deep learning…
In this paper we introduce EfficientPose, a new approach for 6D object pose estimation. Our method is highly accurate, efficient and scalable over a wide range of computational resources. Moreover, it can detect the 2D bounding box of…
Video object segmentation is challenging yet important in a wide variety of applications for video analysis. Recent works formulate video object segmentation as a prediction task using deep nets to achieve appealing state-of-the-art…
Human pose is a useful feature for fine-grained sports action understanding. However, pose estimators are often unreliable when run on sports video due to domain shift and factors such as motion blur and occlusions. This leads to poor…
In this paper, we introduce Attention Prompt Tuning (APT) - a computationally efficient variant of prompt tuning for video-based applications such as action recognition. Prompt tuning approaches involve injecting a set of learnable prompts…
Deep learning video analytic systems process live video feeds from multiple cameras with computer vision models deployed on edge or cloud. To optimize utility for these systems, which usually corresponds to query accuracy, efficient…
Reducing redundancy is crucial for improving the efficiency of video recognition models. An effective approach is to select informative content from the holistic video, yielding a popular family of dynamic video recognition methods.…
Transferring existing image-based detectors to the video is non-trivial since the quality of frames is always deteriorated by part occlusion, rare pose, and motion blur. Previous approaches exploit to propagate and aggregate features across…
Adaptive sampling that exploits the spatiotemporal redundancy in videos is critical for always-on action recognition on wearable devices with limited computing and battery resources. The commonly used fixed sampling strategy is not…
Enabled by large annotated datasets, tracking and segmentation of objects in videos has made remarkable progress in recent years. Despite these advancements, algorithms still struggle under degraded conditions and during fast movements.…
The goal of acoustic (or sound) events detection (AED or SED) is to predict the temporal position of target events in given audio segments. This task plays a significant role in safety monitoring, acoustic early warning and other scenarios.…
Taking advantage of human pose data for understanding human activities has attracted much attention these days. However, state-of-the-art pose estimators struggle in obtaining high-quality 2D or 3D pose data due to occlusion, truncation and…
The goal of fine-grained action recognition is to successfully discriminate between action categories with subtle differences. To tackle this, we derive inspiration from the human visual system which contains specialized regions in the…
Existing scene text spotting (i.e., end-to-end text detection and recognition) methods rely on costly bounding box annotations (e.g., text-line, word-level, or character-level bounding boxes). For the first time, we demonstrate that…
This paper strives for spatio-temporal localization of human actions in videos. In the literature, the consensus is to achieve localization by training on bounding box annotations provided for each frame of each training video. As…