Related papers: FAQ: Feature Aggregated Queries for Transformer-ba…
The rise of autonomous vehicles has significantly increased the demand for robust 3D object detection systems. While cameras and LiDAR sensors each offer unique advantages--cameras provide rich texture information and LiDAR offers precise…
Conventional video segmentation methods often rely on temporal continuity to propagate masks. Such an assumption suffers from issues like drifting and inability to handle large displacement. To overcome these issues, we formulate an…
Multi-sensor modal fusion has demonstrated strong advantages in 3D object detection tasks. However, existing methods that fuse multi-modal features require transforming features into the bird's eye view space and may lose certain…
Recent camera-based 3D object detection methods have introduced sequential frames to improve the detection performance hoping that multiple frames would mitigate the large depth estimation error. Despite improved detection performance,…
We consider the problem of using image queries to retrieve videos from a database. Our focus is on large-scale applications, where it is infeasible to index each database video frame independently. Our main contribution is a framework based…
The influence of atmospheric turbulence on acquired surveillance imagery poses significant challenges in image interpretation and scene analysis. Conventional approaches for target classification and tracking are less effective under such…
Weakly supervised instance segmentation reduces the cost of annotations required to train models. However, existing approaches which rely only on image-level class labels predominantly suffer from errors due to (a) partial segmentation of…
In this paper, we present a solution to Large-Scale Video Classification Challenge (LSVC2017) [1] that ranked the 1st place. We focused on a variety of modalities that cover visual, motion and audio. Also, we visualized the aggregation…
In this paper we propose a geometry-aware model for video object detection. Specifically, we consider the setting that cameras can be well approximated as static, e.g. in video surveillance scenarios, and scene pseudo depth maps can…
We present a novel approach to estimating physical properties of objects from video. Our approach consists of a physics engine and a correction estimator. Starting from the initial observed state, object behavior is simulated forward in…
We present an approach to efficiently and effectively adapt a masked image modeling (MIM) pre-trained vanilla Vision Transformer (ViT) for object detection, which is based on our two novel observations: (i) A MIM pre-trained vanilla ViT…
The problem of video object segmentation can become extremely challenging when multiple instances co-exist. While each instance may exhibit large scale and pose variations, the problem is compounded when instances occlude each other causing…
Intelligent machines require basic information such as moving-object detection from videos in order to deduce higher-level semantic information. In this paper, we propose a methodology that uses a texture measure to detect moving objects in…
Open-vocabulary video visual relationship detection aims to detect objects and their relationships in videos without being restricted by predefined object or relationship categories. Existing methods leverage the rich semantic knowledge of…
Deep neural network approaches have demonstrated high performance in object recognition (CNN) and detection (Faster-RCNN) tasks, but experiments have shown that such architectures are vulnerable to adversarial attacks (FFF, UAP): low…
Effective aggregation of temporal information of consecutive frames is the core of achieving video super-resolution. Many scholars have utilized structures such as sliding windows and recurrent to gather spatio-temporal information of…
Frame-level visual features are generally aggregated in time with the techniques such as LSTM, Fisher Vectors, NetVLAD etc. to produce a robust video-level representation. We here introduce a learnable aggregation technique whose primary…
3D object detection is a core component of automated driving systems. State-of-the-art methods fuse RGB imagery and LiDAR point cloud data frame-by-frame for 3D bounding box regression. However, frame-by-frame 3D object detection suffers…
Adversarial examples have been demonstrated to threaten many computer vision tasks including object detection. However, the existing attacking methods for object detection have two limitations: poor transferability, which denotes that the…
Recently, video object segmentation (VOS) networks typically use memory-based methods: for each query frame, the mask is predicted by space-time matching to memory frames. Despite these methods having superior performance, they suffer from…