40 accepted papers
Linear autoencoders (LAEs) have gained increasing popularity in recommender systems due to their simplicity and strong empirical performance. Most LAE models, including the Emphasized Denoising Linear Autoencoder (EDLAE) introduced by (Steck, 2020), use quadratic loss during training. However, the o…
Uncertainty quantification (UQ) is an important technique for ensuring the trustworthiness of LLMs, given their tendency to hallucinate. Existing state-of-the-art UQ approaches for free-form generation rely heavily on sampling, which incurs high computational cost and variance. In this work, we prop…
3D LiDAR-based gait recognition has gained increasing attention due to its robustness to illumination, privacy preservation, and capability for long-range and non-contact identity verification. However, existing point cloud-based methods suffer from two critical limitations: they fail to model seman
Visual neural decoding seeks to reconstruct or infer perceived visual stimuli from brain activity patterns, providing critical insights into human cognition and enabling transformative applications in brain-computer interfaces and artificial intelligence. Current approaches, however, remain constrai
Large Language Models (LLMs) are increasingly deployed as autonomous agents that execute tool-augmented, multi-step tasks, where latency is a critical factor for real-world applications. Yet an overlooked threat is Reasoning-Level Denial-of-Service (R-DoS), in which an attacker preserves task correc…
Actor-critic (AC) methods are a cornerstone of reinforcement learning (RL) but offer limited interpretability. Current explainable RL methods seldom use *state attributions* to assist training. Rather, they treat all state features equally, thereby neglecting the heterogeneous impacts of individual …
The widespread adoption of artificial intelligence (AI) in cybersecurity has led to the emerging threat of AI-driven cyberattacks, such as LLM-empowered Advanced Persistent Threats (APTs), challenging the effect of conventional deception defense mechanisms. To fill this critical gap, my work aims to
With the accelerated development of Industry 4.0, intelligent manufacturing systems increasingly require efficient task allocation and scheduling in multi-robot systems. However, existing methods rely on domain expertise and face challenges in adapting to dynamic production constraints. Additionally
The existing monocular methods face huge challenges in reconstructing credible details of non-visible areas in large pose images. Due to the fact that facial details are lost in non-visible areas of large pose images, existing methods lose basis when reconstructing details, resulting in unreliable r…
Zero-shot anomaly detection (ZSAD) aims to identify anomalies in new classes of images, and it’s vital in industry and other fields. Most current methods are based on the multimodal models CLIP and SAM, which have prior knowledge to assist model training, but they are highly dependent on the input o…
Garment sewing patterns are fundamental design elements that bridge the gap between design concepts and practical manufacturing. The generative modeling of sewing patterns is crucial for creating diversified garments. However, existing approaches are limited either by reliance on a single input moda
Change detection in synthetic aperture radar (SAR) images is a hot yet highly challenging task in remote sensing. Existing unsupervised SAR change detection methods often struggle with inherent speckle noise and insufficiently utilize pseudo-labels, particularly neglecting uncertain areas. In this p…
Time series forecasting is always important, with multivariate long-term series forecasting being its most challenging task. Here, the existing methods typically learn only in a single domain and focus on optimizing model structures, leading to incomplete information mining and imprecise predictions…
Multi-modal Entity Alignment (MMEA) aims to identify the same entities exhibited in different knowledge graphs (KGs), where the entities are enriched by structure and visual information. Existing MMEA methods learn multi-modal joint entity embeddings by encompassing both modality interaction and mod…
Linear Autoencoders (LAEs) have shown strong performance in state-of-the-art recommender systems. However, this success remains largely empirical, with limited theoretical understanding. In this paper, we investigate the generalizability -- a theoretical measure of model performance in statistical…
Multi-agent reinforcement learning (MARL), as a thriving field, explores how multiple agents independently make decisions in a shared dynamic environment. Due to environmental uncertainties, policies in MARL must remain robust to tackle the sim-to-real gap. We focus on robust two-player zero-sum Mar…
Deep learning models rely on large-scale labeled datasets, but collecting such data is expensive and time-consuming. Semi-supervised learning (SSL) mitigates this issue by learning from a small set of labeled samples along with a large pool of unlabeled data. However, existing SSL methods struggle w…
Recent booming time series models have demonstrated remarkable forecasting performance. However, these methods often place greater focus on more effectively modelling the historical series, largely neglecting the forecasting phase, which generates long-term forecasts by separately predicting multipl…
Fluid resuscitation is an initial treatment frequently employed to treat shock, restore lost blood, protect tissues from injury, and prevent organ dysfunction in critically ill patients. However, it is not without risk (e.g., overly aggressive resuscitation may cause organ damage and even death). We…
"Recent video masked autoencoder (MAE) works have designed improved masking algorithms focused on saliency. These works leverage visual cues such as motion to mask the most salient regions. However, the robustness of such visual cues depends on how often input videos match underlying assumptions. On…
Although Retrieval-Augmented Large Language Models (RALMs) demonstrate their superiority in terms of factuality, they do not consistently outperform the original retrieval-free Language Models (LMs). Our experiments reveal that this example-level performance inconsistency exists not only between ret…
As the scale of data and models for video understanding rapidly expand, handling long-form video input in transformer-based models presents a practical challenge. Rather than resorting to input sampling or token dropping, which may result in information loss, token merging shows promising results wh…
The attention-based Transformers have been increasingly applied to audio classification because of their global receptive field and ability to handle long-term dependency. However, the existing frameworks which are mainly extended from the Vision Transformers are not perfectly compatible with audio…
This study considers the estimation of conditional causal effects in the presence of unmeasured confounding for a balanced panel with treatment imposed at the last time point. To address this, we combine Difference-in-differences (DiD) and tree-based methods and propose a new identification assumpti…
Previous research has studied the task of segmenting cinematic videos into scenes and into narrative acts. However, these studies have overlooked the essential task of multimodal alignment and fusion for effectively and efficiently processing long-form videos (>60min). In this paper, we introduce Mu…
Several recent works have directly extended the image masked autoencoder (MAE) with random masking into video domain, achieving promising results. However, unlike images, both spatial and temporal information are important for video understanding. This suggests that the random masking strategy that…
Contrastive learning-based vision-language pre-training approaches, such as CLIP, have demonstrated great success in many vision-language tasks. These methods achieve cross-modal alignment by encoding a matched image-text pair with similar feature embeddings, which are generated by aggregating infor…
Unmeasured confounding poses a significant threat to the validity of causal inference. Despite that various ad hoc methods are developed to remove confounding effects, they are subject to certain fairly strong assumptions. In this work, we consider the estimation of conditional causal effects in the…
Deep Learning (DL) techniques have been increasingly adopted for Automatic Text Scoring in education. However, these techniques often suffer from their inabilities to explain and justify how a prediction is made, which, unavoidably, decreases their trustworthiness and hinders educators from embracin…
Learning a unified person detection and re-identification model is a key component of modern trackers. However, training such models usually relies on the availability of training images / videos that are manually labeled with both person boxes and their identities. In this work, we explore training…
Extracting arguments for the pre-defined roles is a crucial step for event extraction. Recently, there are some insightful works that view it as a machine reading comprehension problem and achieve significant progress. However, most of them need multi-turns to extract the arguments of each role inde…
We propose a memory efficient method, named Stochastic Backpropagation (SBP), for training deep neural networks on videos. It is based on the finding that gradients from incomplete execution for backpropagation can still effectively train the models with minimal accuracy loss, which attributes to th…
We propose TubeR: a simple solution for spatio-temporal video action detection. Different from existing methods that depend on either an off-line actor detector or hand-designed actor-positional hypotheses like proposals or anchors, we propose to directly detect an action tubelet in video by simulta…
We propose a novel one-stage Transformer-based semantic and spatial refined transformer (SSRT) to solve the Human-Object Interaction detection task, which requires to localize humans and objects, and predicts their interactions. Differently from previous Transformer-based HOI approaches, which mostl…
We present Long Short-term TRansformer (LSTR), a temporal modeling algorithm for online action detection, which employs a long- and short-term memory mechanism to model prolonged sequence data. It consists of an LSTR encoder that dynamically leverages coarse-scale historical information from an exte…
Multi-label activity recognition is designed for recognizing multiple activities that are performed simultaneously or sequentially in each video. Most recent activity recognition networks focus on single-activities, that assume only one activity in each video. These networks extract shared features…
Most action recognition solutions rely on dense sampling to precisely cover the informative temporal clip. Extensively searching temporal region is expensive for a real-world application. In this work, we focus on improving the inference efficiency of current action recognition backbones on trimmed…
In this work, we focus on improving online multi-object tracking (MOT). In particular, we propose a novel region-based Siamese Multi-Object Tracking network, which we name SiamMOT. SiamMOT is based upon Faster-RCNN and adds a forward tracker that models the instance's motion across two frames such t…
We introduce Video Transformer (VidTr) with separable-attention for video classification. Comparing with commonly used 3D networks, VidTr is able to aggregate spatio-temporal information via stacked attentions and provide better performance with higher efficiency. We first introduce the vanilla vide…
Many current activity recognition models use 3D convolutional neural networks (e.g. I3D, I3D-NL) to generate local spatial-temporal features. However, such features do not encode clip-level ordered temporal information. In this paper, we introduce a channel independent directional convolution (CIDC)…