Related papers: INT: Towards Infinite-frames 3D Detection with An …
In surveillance and search and rescue applications, it is important to perform multi-target tracking (MOT) in real-time on low-end devices. Today's MOT solutions employ deep neural networks, which tend to have high computation complexity.…
Resource provisioning in multi-tenant stream processing systems faces the dual challenges of keeping resource utilization high (without over-provisioning), and ensuring performance isolation. In our common production use cases, where…
Single image depth estimation is a foundational task in computer vision and generative modeling. However, prevailing depth estimation models grapple with accommodating the increasing resolutions commonplace in today's consumer cameras and…
With the success of deep learning, object recognition systems that can be deployed for real-world applications are becoming commonplace. However, inference that needs to largely take place on the `edge' (not processed on servers), is a…
Service mobile robots are often required to avoid dynamic objects while performing their tasks, but they usually have only limited computational resources. To further advance the practical application of service robots in complex dynamic…
Query-based transformer has shown great potential in constructing long-range attention in many image-domain tasks, but has rarely been considered in LiDAR-based 3D object detection due to the overwhelming size of the point cloud data. In…
Structured meshes, composed of quadrilateral elements in 2D and hexahedral elements in 3D, are widely used in industrial applications and engineering simulations due to their regularity and superior accuracy in finite element analysis.…
Recently, video frame interpolation using a combination of frame- and event-based cameras has surpassed traditional image-based methods both in terms of performance and memory efficiency. However, current methods still suffer from (i)…
We present Uni$^2$Det, a brand new framework for unified and universal multi-dataset training on 3D detection, enabling robust performance across diverse domains and generalization to unseen domains. Due to substantial disparities in data…
Volumetric models have become a popular representation for 3D scenes in recent years. One breakthrough leading to their popularity was KinectFusion, which focuses on 3D reconstruction using RGB-D sensors. However, monocular SLAM has since…
LiDAR-based 3D single object tracking (3D SOT) is a critical task in robotics and autonomous systems. Existing methods typically follow frame-wise motion estimation or a sequence-based paradigm. However, the two-frame methods are efficient…
In learning-assisted theorem proving, one of the most critical challenges is to generalize to theorems unlike those seen at training time. In this paper, we introduce INT, an INequality Theorem proving benchmark, specifically designed to…
We present a frame interpolation algorithm that synthesizes multiple intermediate frames from two input images with large in-between motion. Recent methods use multiple networks to estimate optical flow or depth and a separate network…
Mobile-centric AI applications have high requirements for resource-efficiency of model inference. Input filtering is a promising approach to eliminate the redundancy so as to reduce the cost of inference. Previous efforts have tailored…
Image sensing often relies on a high-quality machine vision system with a large field of view and high resolution. It requires fine imaging optics, has high computational costs, and requires a large communication bandwidth between image…
As a critical component for online advertising and marking, click-through rate (CTR) prediction has draw lots of attentions from both industry and academia field. Recently, the deep learning has become the mainstream methodological choice…
Recently DRAM-based PIMs (processing-in-memories) with unmodified cell arrays have demonstrated impressive performance for accelerating AI applications. However, due to the very restrictive hardware constraints, PIM remains an accelerator…
We present AdaFrame, a framework that adaptively selects relevant frames on a per-input basis for fast video recognition. AdaFrame contains a Long Short-Term Memory network augmented with a global memory that provides context information…
Given two consecutive frames, video interpolation aims at generating intermediate frame(s) to form both spatially and temporally coherent video sequences. While most existing methods focus on single-frame interpolation, we propose an…
Recent innovations in Transformer-based large language models have significantly advanced the field of general-purpose neural language understanding and generation. With billions of trainable parameters, deployment of these large models…