In this paper, we propose an alternative to deep neural networks for semantic information retrieval for the case of long documents. This new approach exploiting clustering techniques to take into account the meaning of words in Information Retrieval systems targeting long as well as short documents. This approach uses a specially designed clustering algorithm to group words with similar meanings into clusters. The dual representation (lexical and semantic) of documents and queries is based on the vector space model proposed by Gerard Salton in the vector space constituted by the formed clusters. The originalities of our proposal are at several levels: first, we propose an efficient algorithm for the construction of clusters of semantically close words using word embedding as input, then we define a formula for weighting these clusters, and then we propose a function allowing to combine efficiently the meanings of words with a lexical model widely used in Information Retrieval. The evaluation of our proposal in three contexts with two different datasets SQuAD and TREC-CAR has shown that is significantly improves the classical approaches only based on the keywords without degrading the lexical aspect.
Relation-focused cross-modal information retrieval focuses on retrieving information based on relations expressed in user queries, and it is particularly important in information retrieval applications and next-generation search engines. To date, CLIP (Contrastive Language-Image Pre-training) achieved state-of-the-art performance in cross-modal learning tasks due to its efficient learning of visual concepts from natural language supervision. However, CLIP learns visual representations from natural language at a global level without the capability of focusing on image-object relations. This paper proposes a novel CLIP-based network for Relation Reasoning, CLIP-RR, that tackles relation-focused cross-modal information retrieval. The proposed network utilises CLIP to leverage its pre-trained knowledge, and it additionally comprises two main parts: (1) extends the capabilities of CLIP to extract and reason with object relations in images; and (2) aggregates the reasoned results for predicting the similarity scores between images and descriptions. Experiments were carried out by applying the proposed network to relation-focused cross-modal information retrieval tasks on the RefCOCOg, CLEVR, and Flickr30K datasets. The results revealed that the proposed network outperformed various other state-of-the-art networks including CLIP, VSE$\infty$, and VSRN++ on both image-to-text and text-to-image cross-modal information retrieval tasks.
In this paper, we propose a digital twin (DT)-assisted resource demand prediction scheme to enhance prediction accuracy for multicast short video streaming. Particularly, we construct user DTs (UDTs) for collecting real-time user status, including channel condition, location, watching duration, and preference. A reinforcement learning-empowered K-means++ algorithm is developed to cluster users based on the collected user status in UDTs, which can effectively employ the mined users' intrinsic correlation to improve the accuracy of user clustering. We then analyze users' video watching duration and preferences in each multicast group to obtain the swiping probability distribution and recommended videos, respectively. The obtained information is utilized to predict radio and computing resource demand of each multicast group. Initial results demonstrate that the proposed scheme can effectively abstract multicast groups' swiping probability distributions for accurate resource demand prediction.
Video scene parsing incorporates temporal information, which can enhance the consistency and accuracy of predictions compared to image scene parsing. The added temporal dimension enables a more comprehensive understanding of the scene, leading to more reliable results. This paper presents the winning solution of the CVPR2023 workshop for video semantic segmentation, focusing on enhancing Spatial-Temporal correlations with contrastive loss. We also explore the influence of multi-dataset training by utilizing a label-mapping technique. And the final result is aggregating the output of the above two models. Our approach achieves 65.95% mIoU performance on the VSPW dataset, ranked 1st place on the VSPW challenge at CVPR 2023.
Inductive relation reasoning for knowledge graphs, aiming to infer missing links between brand-new entities, has drawn increasing attention. The models developed based on Graph Inductive Learning, called GraIL-based models, have shown promising potential for this task. However, the uni-directional message-passing mechanism hinders such models from exploiting hidden mutual relations between entities in directed graphs. Besides, the enclosing subgraph extraction in most GraIL-based models restricts the model from extracting enough discriminative information for reasoning. Consequently, the expressive ability of these models is limited. To address the problems, we propose a novel GraIL-based inductive relation reasoning model, termed MINES, by introducing a Message Intercommunication mechanism on the Neighbor-Enhanced Subgraph. Concretely, the message intercommunication mechanism is designed to capture the omitted hidden mutual information. It introduces bi-directed information interactions between connected entities by inserting an undirected/bi-directed GCN layer between uni-directed RGCN layers. Moreover, inspired by the success of involving more neighbors in other graph-based tasks, we extend the neighborhood area beyond the enclosing subgraph to enhance the information collection for inductive relation reasoning. Extensive experiments on twelve inductive benchmark datasets demonstrate that our MINES outperforms existing state-of-the-art models, and show the effectiveness of our intercommunication mechanism and reasoning on the neighbor-enhanced subgraph.
The reliability of current autonomous driving systems is often jeopardized in situations when the vehicle's field-of-view is limited by nearby occluding objects. To mitigate this problem, vehicle-to-vehicle communication to share sensor information among multiple autonomous driving vehicles has been proposed. However, to enable timely processing and use of shared sensor data, it is necessary to constrain communication bandwidth, and prior work has done so by restricting the number of other cooperative vehicles and randomly selecting the subset of vehicles to exchange information with from all those that are within communication range. Although simple and cost effective from a communication perspective, this selection approach suffers from its susceptibility to missing those vehicles that possess the perception information most critical to navigation planning. Inspired by recent multi-agent path finding research, we propose a novel selective communication algorithm for cooperative perception to address this shortcoming. Implemented with a lightweight perception network and a previously developed control network, our algorithm is shown to produce higher success rates than a random selection approach on previously studied safety-critical driving scenario simulations, with minimal additional communication overhead.
To automate harvesting and de-leafing of tomato plants using robots, it is important to search and detect the relevant plant parts, namely tomatoes, peduncles, and petioles. This is challenging due to high levels of occlusion in tomato greenhouses. Active vision is a promising approach which helps robots to deliberately plan camera viewpoints to overcome occlusion and improve perception accuracy. However, current active-vision algorithms cannot differentiate between relevant and irrelevant plant parts, making them inefficient for targeted perception of specific plant parts. We propose a semantic active-vision strategy that uses semantic information to identify the relevant plant parts and prioritises them during view planning using an attention mechanism. We evaluated our strategy using 3D models of tomato plants with varying structural complexity, which closely represented occlusions in the real world. We used a simulated environment to gain insights into our strategy, while ensuring repeatability and statistical significance. At the end of ten viewpoints, our strategy was able to correctly detect 85.5% of the plant parts, about 4 parts more on average per plant compared to a volumetric active-vision strategy. Also, it detected 5 and 9 parts more compared to two predefined strategies and 11 parts more compared to a random strategy. It also performed reliably with a median of 88.9% correctly-detected objects per plant in 96 experiments. Our strategy was also robust to uncertainty in plant and plant-part position, plant complexity, and different viewpoint sampling strategies. We believe that our work could significantly improve the speed and robustness of automated harvesting and de-leafing in tomato crop production.
Tabular data is arguably one of the most commonly used data structures in various practical domains, including finance, healthcare and e-commerce. The inherent heterogeneity allows tabular data to store rich information. However, based on a recently published tabular benchmark, we can see deep neural networks still fall behind tree-based models on tabular datasets. In this paper, we propose Trompt--which stands for Tabular Prompt--a novel architecture inspired by prompt learning of language models. The essence of prompt learning is to adjust a large pre-trained model through a set of prompts outside the model without directly modifying the model. Based on this idea, Trompt separates the learning strategy of tabular data into two parts. The first part, analogous to pre-trained models, focus on learning the intrinsic information of a table. The second part, analogous to prompts, focus on learning the variations among samples. Trompt is evaluated with the benchmark mentioned above. The experimental results demonstrate that Trompt outperforms state-of-the-art deep neural networks and is comparable to tree-based models.
In real-world tasks, there is usually a large amount of unlabeled data and labeled data. The task of combining the two to learn is known as semi-supervised learning. Experts can use logical rules to label unlabeled data, but this operation is costly. The combination of perception and reasoning has a good effect in processing such semi-supervised tasks with domain knowledge. However, acquiring domain knowledge and the correction, reduction and generation of rules remain complex problems to be solved. Rough set theory is an important method for solving knowledge processing in information systems. In this paper, we propose a rule general abductive learning by rough set (RS-ABL). By transforming the target concept and sub-concepts of rules into information tables, rough set theory is used to solve the acquisition of domain knowledge and the correction, reduction and generation of rules at a lower cost. This framework can also generate more extensive negative rules to enhance the breadth of the knowledge base. Compared with the traditional semi-supervised learning method, RS-ABL has higher accuracy in dealing with semi-supervised tasks.
This paper presents a novel transformer-based framework for unsupervised activity segmentation which leverages not only frame-level cues but also segment-level cues. This is in contrast with previous methods which often rely on frame-level information only. Our approach begins with a frame-level prediction module which estimates framewise action classes via a transformer encoder. The frame-level prediction module is trained in an unsupervised manner via temporal optimal transport. To exploit segment-level information, we introduce a segment-level prediction module and a frame-to-segment alignment module. The former includes a transformer decoder for estimating video transcripts, while the latter matches frame-level features with segment-level features, yielding permutation-aware segmentation results. Moreover, inspired by temporal optimal transport, we develop simple-yet-effective pseudo labels for unsupervised training of the above modules. Our experiments on four public datasets, i.e., 50 Salads, YouTube Instructions, Breakfast, and Desktop Assembly show that our approach achieves comparable or better performance than previous methods in unsupervised activity segmentation.