Related papers: Locality-aware Cross-modal Correspondence Learning…
We present a self-supervised learning approach to learn audio-visual representations from video and audio. Our method uses contrastive learning for cross-modal discrimination of video from audio and vice-versa. We show that optimizing for…
An objective understanding of media depictions, such as inclusive portrayals of how much someone is heard and seen on screen such as in film and television, requires the machines to discern automatically who, when, how, and where someone is…
Leveraging temporal information has been regarded as essential for developing video understanding models. However, how to properly incorporate temporal information into the recent successful instance discrimination based contrastive…
Human Object Interaction (HOI) detection aims to localize and infer the relationships between a human and an object. Arguably, training supervised models for this task from scratch presents challenges due to the performance drop over rare…
Recent multi-modal audio-language models (ALMs) excel at text-audio retrieval but struggle with frame-wise audio understanding. Prior works use temporal-aware labels or unsupervised training to improve frame-wise capabilities, but they…
Recent advances in learned video compression (LVC) have led to significant performance gains, with codecs such as DCVC-RT surpassing the H.266/VVC low-delay mode in compression efficiency. However, existing LVCs still exhibit key…
Robust frame-wise embeddings are essential to perform video analysis and understanding tasks. We present a self-supervised method for representation learning based on aligning temporal video sequences. Our framework uses a transformer-based…
Vision-and-Language navigation (VLN) requires an agent to navigate in unseen environment by following natural language instruction. For task completion, the agent needs to align and integrate various navigation modalities, including…
Dense video captioning jointly localizes and captions salient events in untrimmed videos. Recent methods primarily focus on leveraging additional prior knowledge and advanced multi-task architectures to achieve competitive performance.…
Unsupervised domain adaptive (UDA) algorithms can markedly enhance the performance of object detectors under conditions of domain shifts, thereby reducing the necessity for extensive labeling and retraining. Current domain adaptive object…
Learning common subspace is prevalent way in cross-modal retrieval to solve the problem of data from different modalities having inconsistent distributions and representations that cannot be directly compared. Previous cross-modal retrieval…
Recent advances in representation learning have demonstrated an ability to represent information from different modalities such as video, text, and audio in a single high-level embedding vector. In this work we present a self-supervised…
Audiovisual scenes are pervasive in our daily life. It is commonplace for humans to discriminatively localize different sounding objects but quite challenging for machines to achieve class-aware sounding objects localization without…
There has been a long-standing quest for a unified audio-visual-text model to enable various multimodal understanding tasks, which mimics the listening, seeing and reading process of human beings. Humans tends to represent knowledge using…
Speech enhancement (SE) aims to improve the quality and intelligibility of speech in noisy environments. Recent studies have shown that incorporating visual cues in audio signal processing can enhance SE performance. Given that human speech…
Learned image compression (LIC) increasingly requires reconstructions that balance distortion fidelity and perceptual realism across a wide range of bitrates. However, most existing methods still rely on a single compressed latent…
When watching videos, the occurrence of a visual event is often accompanied by an audio event, e.g., the voice of lip motion, the music of playing instruments. There is an underlying correlation between audio and visual events, which can be…
Understanding and reasoning over long contexts is a crucial capability for language models (LMs). Although recent models support increasingly long context windows, their accuracy often deteriorates as input length grows. In practice, models…
Multimodal learning seeks to integrate information across diverse sensory sources, yet current approaches struggle to balance cross-modal generalizability with modality-specific structure. Continuous (implicit) methods preserve fine-grained…
Most existing vision encoders map images into a fixed-length sequence of tokens, overlooking the fact that different images contain varying amounts of information. For example, a visually complex image (e.g., a cluttered room) inherently…