Tracking and segmenting multiple similar objects with complex or separate parts in long-term videos is inherently challenging due to the ambiguity of target parts and identity confusion caused by occlusion, background clutter, and long-term variations. In this paper, we propose a robust video object segmentation framework equipped with spatial-semantic features and discriminative object queries to address the above issues. Specifically, we construct a spatial-semantic network comprising a semantic embedding block and spatial dependencies modeling block to associate the pretrained ViT features with global semantic features and local spatial features, providing a comprehensive target representation. In addition, we develop a masked cross-attention module to generate object queries that focus on the most discriminative parts of target objects during query propagation, alleviating noise accumulation and ensuring effective long-term query propagation. The experimental results show that the proposed method set a new state-of-the-art performance on multiple datasets, including the DAVIS2017 test (89.1%), YoutubeVOS 2019 (88.5%), MOSE (75.1%), LVOS test (73.0%), and LVOS val (75.1%), which demonstrate the effectiveness and generalization capacity of the proposed method. We will make all source code and trained models publicly available.

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 two issues: 1) Challenging data can destroy the space-time coherence between adjacent video frames. 2) Pixel-level matching will lead to undesired mismatching caused by the noises or distractors. To address the aforementioned issues, we first propose to generate an auxiliary frame between adjacent frames, serving as an implicit short-temporal reference for the query one. Next, we learn a prototype for each video object and prototype-level matching can be implemented between the query and memory. The experiment demonstrated that our network outperforms the state-of-the-art method on the DAVIS 2017, achieving a J&F score of 86.4%, and attains a competitive result 85.0% on YouTube VOS 2018. In addition, our network exhibits a high inference speed of 32+ FPS.

Dynamic scene understanding is one of the most conspicuous field of interest among computer vision community. In order to enhance dynamic scene understanding, pixel-wise segmentation with neural networks is widely accepted. The latest researches on pixel-wise segmentation combined semantic and motion information and produced good performance. In this work, we propose a state of art architecture of neural networks to accurately and efficiently get the moving object proposals (MOP). We first train an unsupervised convolutional neural network (UnFlow) to generate optical flow estimation. Then we render the output of optical flow net to a fully convolutional SegNet model. The main contribution of our work is (1) Fine-tuning the pretrained optical flow model on the brand new DAVIS Dataset; (2) Leveraging fully convolutional neural networks with Encoder-Decoder architecture to segment objects. We developed the codes with TensorFlow, and executed the training and evaluation processes on an AWS EC2 instance.

Recent self-supervised learning (SSL) methods have shown impressive results in learning visual representations from unlabeled images. This paper aims to improve their performance further by utilizing the architectural advantages of the underlying neural network, as the current state-of-the-art visual pretext tasks for SSL do not enjoy the benefit, i.e., they are architecture-agnostic. In particular, we focus on Vision Transformers (ViTs), which have gained much attention recently as a better architectural choice, often outperforming convolutional networks for various visual tasks. The unique characteristic of ViT is that it takes a sequence of disjoint patches from an image and processes patch-level representations internally. Inspired by this, we design a simple yet effective visual pretext task, coined SelfPatch, for learning better patch-level representations. To be specific, we enforce invariance against each patch and its neighbors, i.e., each patch treats similar neighboring patches as positive samples. Consequently, training ViTs with SelfPatch learns more semantically meaningful relations among patches (without using human-annotated labels), which can be beneficial, in particular, to downstream tasks of a dense prediction type. Despite its simplicity, we demonstrate that it can significantly improve the performance of existing SSL methods for various visual tasks, including object detection and semantic segmentation. Specifically, SelfPatch significantly improves the recent self-supervised ViT, DINO, by achieving +1.3 AP on COCO object detection, +1.2 AP on COCO instance segmentation, and +2.9 mIoU on ADE20K semantic segmentation.

We propose a novel visual memory network architecture for the learning and inference problem in the spatial-temporal domain. Different from the popular transformers, we maintain a fixed set of memory slots in our memory network and explore designs to input new information into the memory, combine the information in different memory slots and decide when to discard old memory slots. Finally, this architecture is benchmarked on the video object segmentation and video prediction problems. Through the experiments, we show that our memory architecture can achieve competitive results with state-of-the-art while maintaining constant memory capacity.