Actions are about how we interact with the environment, including other people, objects, and ourselves. In this paper, we propose a novel multi-modal Holistic Interaction Transformer Network (HIT) that leverages the largely ignored, but critical hand and pose information essential to most human actions. The proposed "HIT" network is a comprehensive bi-modal framework that comprises an RGB stream and a pose stream. Each of them separately models person, object, and hand interactions. Within each sub-network, an Intra-Modality Aggregation module (IMA) is introduced that selectively merges individual interaction units. The resulting features from each modality are then glued using an Attentive Fusion Mechanism (AFM). Finally, we extract cues from the temporal context to better classify the occurring actions using cached memory. Our method significantly outperforms previous approaches on the J-HMDB, UCF101-24, and MultiSports datasets. We also achieve competitive results on AVA. The code will be available at https://github.com/joslefaure/HIT.
We study the evolution of latent space in fine-tuned NLP models. Different from the commonly used probing-framework, we opt for an unsupervised method to analyze representations. More specifically, we discover latent concepts in the representational space using hierarchical clustering. We then use an alignment function to gauge the similarity between the latent space of a pre-trained model and its fine-tuned version. We use traditional linguistic concepts to facilitate our understanding and also study how the model space transforms towards task-specific information. We perform a thorough analysis, comparing pre-trained and fine-tuned models across three models and three downstream tasks. The notable findings of our work are: i) the latent space of the higher layers evolve towards task-specific concepts, ii) whereas the lower layers retain generic concepts acquired in the pre-trained model, iii) we discovered that some concepts in the higher layers acquire polarity towards the output class, and iv) that these concepts can be used for generating adversarial triggers.
Facial expression is one of the most external indications of a person's feelings and emotions. In daily conversation, according to the psychologist, only 7\% and 38\% of information is communicated through words and sounds respective, while up to 55\% is through facial expression. It plays an important role in coordinating interpersonal relationships. Ekman and Friesen recognized six essential emotions in the nineteenth century depending on a cross-cultural study, which indicated that people feel each basic emotion in the same fashion despite culture. As a branch of the field of analyzing sentiment, facial expression recognition offers broad application prospects in a variety of domains, including the interaction between humans and computers, healthcare, and behavior monitoring. Therefore, many researchers have devoted themselves to facial expression recognition. In this paper, an effective hybrid data augmentation method is used. This approach is operated on two public datasets, and four benchmark models see some remarkable results.
Most existing methods in vision-language retrieval match two modalities by either comparing their global feature vectors which misses sufficient information and lacks interpretability, detecting objects in images or videos and aligning the text with fine-grained features which relies on complicated model designs, or modeling fine-grained interaction via cross-attention upon visual and textual tokens which suffers from inferior efficiency. To address these limitations, some recent works simply aggregate the token-wise similarities to achieve fine-grained alignment, but they lack intuitive explanations as well as neglect the relationships between token-level features and global representations with high-level semantics. In this work, we rethink fine-grained cross-modal alignment and devise a new model-agnostic formulation for it. We additionally demystify the recent popular works and subsume them into our scheme. Furthermore, inspired by optimal transport theory, we introduce TokenFlow, an instantiation of the proposed scheme. By modifying only the similarity function, the performance of our method is comparable to the SoTA algorithms with heavy model designs on major video-text retrieval benchmarks. The visualization further indicates that TokenFlow successfully leverages the fine-grained information and achieves better interpretability.
Multi-armed bandit (MAB) problems are mainly studied under two extreme settings known as stochastic and adversarial. These two settings, however, do not capture realistic environments such as search engines and marketing and advertising, in which rewards stochastically change in time. Motivated by that, we introduce and study a dynamic MAB problem with stochastic temporal structure, where the expected reward of each arm is governed by an auto-regressive (AR) model. Due to the dynamic nature of the rewards, simple "explore and commit" policies fail, as all arms have to be explored continuously over time. We formalize this by characterizing a per-round regret lower bound, where the regret is measured against a strong (dynamic) benchmark. We then present an algorithm whose per-round regret almost matches our regret lower bound. Our algorithm relies on two mechanisms: (i) alternating between recently pulled arms and unpulled arms with potential, and (ii) restarting. These mechanisms enable the algorithm to dynamically adapt to changes and discard irrelevant past information at a suitable rate. In numerical studies, we further demonstrate the strength of our algorithm under different types of non-stationary settings.
Membership Inference Attacks (MIAs) infer whether a data point is in the training data of a machine learning model. It is a threat while being in the training data is private information of a data point. MIA correctly infers some data points as members or non-members of the training data. Intuitively, data points that MIA accurately detects are vulnerable. Considering those data points may exist in different target models susceptible to multiple MIAs, the vulnerability of data points under multiple MIAs and target models is worth exploring. This paper defines new metrics that can reflect the actual situation of data points' vulnerability and capture vulnerable data points under multiple MIAs and target models. From the analysis, MIA has an inference tendency to some data points despite a low overall inference performance. Additionally, we implement 54 MIAs, whose average attack accuracy ranges from 0.5 to 0.9, to support our analysis with our scalable and flexible platform, Membership Inference Attacks Platform (VMIAP). Furthermore, previous methods are unsuitable for finding vulnerable data points under multiple MIAs and different target models. Finally, we observe that the vulnerability is not characteristic of the data point but related to the MIA and target model.
In this paper, we initiate the study of local model reconstruction attacks for federated learning, where a honest-but-curious adversary eavesdrops the messages exchanged between a targeted client and the server, and then reconstructs the local/personalized model of the victim. The local model reconstruction attack allows the adversary to trigger other classical attacks in a more effective way, since the local model only depends on the client's data and can leak more private information than the global model learned by the server. Additionally, we propose a novel model-based attribute inference attack in federated learning leveraging the local model reconstruction attack. We provide an analytical lower-bound for this attribute inference attack. Empirical results using real world datasets confirm that our local reconstruction attack works well for both regression and classification tasks. Moreover, we benchmark our novel attribute inference attack against the state-of-the-art attacks in federated learning. Our attack results in higher reconstruction accuracy especially when the clients' datasets are heterogeneous. Our work provides a new angle for designing powerful and explainable attacks to effectively quantify the privacy risk in FL.
[18F]-Fluorodeoxyglucose (FDG) positron emission tomography - computed tomography (PET-CT) has become the imaging modality of choice for diagnosing many cancers. Co-learning complementary PET-CT imaging features is a fundamental requirement for automatic tumor segmentation and for developing computer aided cancer diagnosis systems. We propose a hyper-connected transformer (HCT) network that integrates a transformer network (TN) with a hyper connected fusion for multi-modality PET-CT images. The TN was leveraged for its ability to provide global dependencies in image feature learning, which was achieved by using image patch embeddings with a self-attention mechanism to capture image-wide contextual information. We extended the single-modality definition of TN with multiple TN based branches to separately extract image features. We introduced a hyper connected fusion to fuse the contextual and complementary image features across multiple transformers in an iterative manner. Our results with two non-small cell lung cancer and soft-tissue sarcoma datasets show that HCT achieved better performance in segmentation accuracy when compared to state-of-the-art methods. We also show that HCT produces consistent performance across various image fusion strategies and network backbones.
We present a game benchmark for testing human-swarm control algorithms and interfaces in a real-time, high-cadence scenario. Our benchmark consists of a swarm vs. swarm game in a virtual ROS environment in which the goal of the game is to capture all agents from the opposing swarm; the game's high-cadence is a result of the capture rules, which cause agent team sizes to fluctuate rapidly. These rules require players to consider both the number of agents currently at their disposal and the behavior of their opponent's swarm when they plan actions. We demonstrate our game benchmark with a default human-swarm control system that enables a player to interact with their swarm through a high-level touchscreen interface. The touchscreen interface transforms player gestures into swarm control commands via a low-level decentralized ergodic control framework. We compare our default human-swarm control system to a flocking-based control system, and discuss traits that are crucial for swarm control algorithms and interfaces operating in real-time, high-cadence scenarios like our game benchmark. Our game benchmark code is available on Github; more information can be found at https://sites.google.com/view/swarm-game-benchmark.
This study presents UX-Net, a time-domain audio separation network (TasNet) based on a modified U-Net architecture. The proposed UX-Net works in real-time and handles either single or multi-microphone input. Inspired by the filter-and-process-based human auditory behavior, the proposed system introduces novel mixer and separation modules, which result in cost and memory efficient modeling of speech sources. The mixer module combines encoded input in a latent feature space and outputs a desired number of output streams. Then, in the separation module, a modified U-Net (UX) block is applied. The UX block first filters the encoded input at various resolutions followed by aggregating the filtered information and applying recurrent processing to estimate masks of separated sources. The letter 'X' in UX-Net is a name placeholder for the type of recurrent layer employed in the UX block. Empirical findings on the WSJ0-2mix benchmark dataset show that one of the UX-Net configurations outperforms the state-of-the-art Conv-TasNet system by 0.85 dB SI-SNR while using only 16% of the model parameters, 58% fewer computations, and maintaining low latency.