3 December 2020 in IEEE Transactions on Image Processing
Anticipating actions before they are executed is crucial for a wide range of practical applications, including autonomous driving and robotics. In this paper, we study the egocentric action anticipation task, which predicts future action seconds before it is performed for egocentric videos. Previous approaches focus on summarizing the observed content and directly predicting future action based on past observations. We believe it would benefit the action anticipation if we could mine some cues to compensate for the missing information of the unobserved frames. We then propose to decompose the action anticipation into a series of future feature predictions. We imagine how the visual feature changes in the near future and then predicts future action labels based on these imagined representations. Differently, our ImagineRNN is optimized in a contrastive learning way instead of feature regression. We utilize a proxy task to train the ImagineRNN, i.e., selecting the correct future states from distractors. We further improve ImagineRNN by residual anticipation, i.e., changing its target to predicting the feature difference of adjacent frames instead of the frame content. This promotes the network to focus on our target, i.e., the future action, as the difference between adjacent frame features is more important for forecasting the future. Extensive experiments on two large-scale egocentric action datasets validate the effectiveness of our method. Our method significantly outperforms previous methods on both the seen test set and the unseen test set of the EPIC Kitchens Action Anticipation Challenge.
5 September 2022 in IEEE Transactions on Multimedia
Text-video retrieval is one of the basic tasks for multimodal research and has been widely harnessed in many real-world systems. Most existing approaches directly compare the global representation between videos and text descriptions and utilize the global contrastive loss to train the model. These designs overlook the local alignment and the word-level supervision signal. In this paper, we propose a new framework, called Align and Tell, for text-video retrieval. Compared to the previous work, our framework contains additional modules, i.e., two transformer decoders for local alignment and one captioning head to enhance the representation learning. First, we introduce a set of learnable queries to interact with both textual representations and video representations and project them to a fixed number of local features. After that, local contrastive learning is performed to complement the global comparison. Moreover, we design a video captioning head to provide additional supervision signals during training. This word-level supervision can enhance the visual presentation and alleviate the cross-modal gap. The captioning head can be removed during inference and does not introduce extra computational costs. Extensive empirical results demonstrate that our Align and Tell model can achieve state-of-the-art performance on four text-video retrieval datasets, including MSR-VTT, MSVD, LSMDC, and ActivityNet-Captions.
31 October 2022 in IEEE Transactions on Neural Networks and Learning Systems
People live in a 3D world. However, existing works on person re-identification (re-id) mostly consider the semantic representation learning in a 2D space, intrinsically limiting the understanding of people. In this work, we address this limitation by exploring the prior knowledge of the 3D body structure. Specifically, we project 2D images to a 3D space and introduce a novel parameter-efficient omni-scale graph network (OG-Net) to learn the pedestrian representation directly from 3D point clouds. OG-Net effectively exploits the local information provided by sparse 3D points and takes advantage of the structure and appearance information in a coherent manner. With the help of 3D geometry information, we can learn a new type of deep re-id feature free from noisy variants, such as scale and viewpoint. To our knowledge, we are among the first attempts to conduct person re-id in the 3D space. We demonstrate through extensive experiments that the proposed method: (1) eases the matching difficulty in the traditional 2D space; 2) exploits the complementary information of 2D appearance and 3D structure; 3) achieves competitive results with limited parameters on four large-scale person re-id datasets; and 4) has good scalability to unseen datasets. Our code, models, and generated 3D human data are publicly available at https://github.com/layumi/person-reid-3d.
24 March 2024 in Proceedings of the AAAI Conference on Artificial Intelligence
Text-video retrieval is a critical multi-modal task to find the most relevant video for a text query. Although pretrained models like CLIP have demonstrated impressive potential in this area, the rising cost of fully finetuning these models due to increasing model size continues to pose a problem. To address this challenge, prompt tuning has emerged as an alternative. However, existing works still face two problems when adapting pretrained image-text models to downstream video-text tasks: (1) The visual encoder could only encode frame-level features and failed to extract global-level general video information. (2) Equipping the visual and text encoder with separated prompts failed to mitigate the visual-text modality gap. To this end, we propose DGL, a cross-modal Dynamic prompt tuning method with Global-Local video attention. In contrast to previous prompt tuning methods, we employ the shared latent space to generate local-level text and frame prompts that encourage inter-modal interaction. Furthermore, we propose modeling video in a global-local attention mechanism to capture global video information from the perspective of prompt tuning. Extensive experiments reveal that when only 0.67% parameters are tuned, our cross-modal prompt tuning strategy DGL outperforms or is comparable to fully finetuning methods on MSR-VTT, VATEX, LSMDC, and ActivityNet datasets. Code will be available at https://github.com/knightyxp/DGL.
28 December 2021 in IEEE Transactions on Visualization and Computer Graphics
As training high-performance object detectors requires expensive bounding box annotations, recent methods resort to free-available image captions. However, detectors trained on caption supervision perform poorly because captions are usually noisy and cannot provide precise location information. To tackle this issue, we present a visual analysis method, which tightly integrates caption supervision with object detection to mutually enhance each other. In particular, object labels are first extracted from captions, which are utilized to train the detectors. Then, the objects detected from images are fed into caption supervision for further improvement. To effectively loop users into the object detection process, a node-link-based set visualization supported by a multi-type relational co-clustering algorithm is developed to explain the relationships between the extracted labels and the images with detected objects. The co-clustering algorithm clusters labels and images simultaneously by utilizing both their representations and their relationships. Quantitative evaluations and a case study are conducted to demonstrate the efficiency and effectiveness of the developed method in improving the performance of object detectors.
2 April 2024 in IEEE Transactions on Pattern Analysis and Machine Intelligence
This paper delves into the challenges of achieving scalable and effective multi-object modeling for semi-supervised Video Object Segmentation (VOS). Previous VOS methods decode features with a single positive object, limiting the learning of multi-object representation as they must match and segment each target separately under multi-object scenarios. Additionally, earlier techniques catered to specific application objectives and lacked the flexibility to fulfill different speed-accuracy requirements. To address these problems, we present two innovative approaches, Associating Objects with Transformers (AOT) and Associating Objects with Scalable Transformers (AOST). In pursuing effective multi-object modeling, AOT introduces the IDentification (ID) mechanism to allocate each object a unique identity. This approach enables the network to model the associations among all objects simultaneously, thus facilitating the tracking and segmentation of objects in a single network pass. To address the challenge of inflexible deployment, AOST further integrates scalable long short-term transformers that incorporate scalable supervision and layer-wise ID-based attention. This enables online architecture scalability in VOS for the first time and overcomes ID embeddings' representation limitations. Given the absence of a benchmark for VOS involving densely multi-object annotations, we propose a challenging Video Object Segmentation in the Wild (VOSW) benchmark to validate our approaches. We evaluated various AOT and AOST variants using extensive experiments across VOSW and five commonly used VOS benchmarks, including YouTube-VOS 2018 & 2019 Val, DAVIS-2017 Val & Test, and DAVIS-2016. Our approaches surpass the state-of-the-art competitors and display exceptional efficiency and scalability consistently across all six benchmarks. Moreover, we notably achieved the $\mathbf {1^{st}}$ position in the 3 rd Large-scale Video Object Segmentation Challenge. Project page: https://github.com/yoxu515/aot-benchmark .